```
├── LICENSE (omitted)
├── README-CN.md (1700 tokens)
├── README.md (2.3k tokens)
├── assets/
├── demo/
├── latex_proj/
├── fancyhdr.sty (4.1k tokens)
├── figure/
├── data_stat.pdf
├── eval.pdf
├── human_evaluation_bar.pdf
├── icon.png
├── logo.png
├── logo_.png
├── mcts.pdf
├── method.pdf
├── paper_topics_wordcloud.pdf
├── presenter.png
├── slides_count_hist.pdf
├── teaser.pdf
├── tree_search.pdf
├── tree_search_vis.pdf
├── video_length_hist.pdf
├── vis.pdf
├── visual.pdf
├── iclr2025_conference.bib (4.3k tokens)
├── iclr2025_conference.bst (5.4k tokens)
├── iclr2025_conference.pdf
├── iclr2025_conference.sty (1800 tokens)
├── iclr2025_conference.tex (1300 tokens)
├── iclr2026_paper.sty (1800 tokens)
├── math_commands.tex (2.5k tokens)
├── natbib.sty (9k tokens)
├── section/
├── appendix.tex (4.4k tokens)
├── benchmark.tex (2.9k tokens)
├── checklist.tex (5.2k tokens)
├── conclusion.tex (100 tokens)
├── experiment.tex (2.7k tokens)
├── introduction.tex (2.3k tokens)
├── method.tex (3.3k tokens)
├── related_work.tex (1300 tokens)
├── slides.tex (3k tokens)
├── zeyu.png
├── zeyu.wav
├── logo.png
├── method.png
├── metrics.png
├── paper2video.mp4
├── sound.png
├── teaser.png
├── src/
├── 1_merage.bash (300 tokens)
├── 1_merage_light.bash (400 tokens)
├── 1_merage_wo_talkinghead.bash (400 tokens)
├── cursor_gen.py (1700 tokens)
├── cursor_image/
├── red.png
├── cursor_render.py (800 tokens)
├── evaluation/
├── IPMemory/
├── construct.py (500 tokens)
├── ip_qa.py (1300 tokens)
├── MetaSim_audio.py (900 tokens)
├── MetaSim_content.py (1100 tokens)
├── PresentArena.py (800 tokens)
├── PresentQuiz/
├── PresentQuiz.py (2.1k tokens)
├── create_paper_questions.py (300 tokens)
├── docling/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── __init__.cpython-39.pyc (omitted)
├── document_converter.cpython-310.pyc (omitted)
├── document_converter.cpython-312.pyc (omitted)
├── exceptions.cpython-310.pyc (omitted)
├── exceptions.cpython-312.pyc (omitted)
├── backend/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── abstract_backend.cpython-310.pyc (omitted)
├── abstract_backend.cpython-312.pyc (omitted)
├── asciidoc_backend.cpython-310.pyc (omitted)
├── asciidoc_backend.cpython-312.pyc (omitted)
├── docling_parse_backend.cpython-310.pyc (omitted)
├── docling_parse_v2_backend.cpython-310.pyc (omitted)
├── docling_parse_v2_backend.cpython-312.pyc (omitted)
├── html_backend.cpython-310.pyc (omitted)
├── html_backend.cpython-312.pyc (omitted)
├── md_backend.cpython-310.pyc (omitted)
├── md_backend.cpython-312.pyc (omitted)
├── msexcel_backend.cpython-310.pyc (omitted)
├── msexcel_backend.cpython-312.pyc (omitted)
├── mspowerpoint_backend.cpython-310.pyc (omitted)
├── mspowerpoint_backend.cpython-312.pyc (omitted)
├── msword_backend.cpython-310.pyc (omitted)
├── msword_backend.cpython-312.pyc (omitted)
├── pdf_backend.cpython-310.pyc (omitted)
├── pdf_backend.cpython-312.pyc (omitted)
├── pypdfium2_backend.cpython-310.pyc (omitted)
├── abstract_backend.py (300 tokens)
├── asciidoc_backend.py (2.8k tokens)
├── docling_parse_backend.py (1500 tokens)
├── docling_parse_v2_backend.py (1700 tokens)
├── html_backend.py (3.2k tokens)
├── json/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── docling_json_backend.cpython-310.pyc (omitted)
├── docling_json_backend.cpython-312.pyc (omitted)
├── docling_json_backend.py (400 tokens)
├── md_backend.py (3.4k tokens)
├── msexcel_backend.py (2.5k tokens)
├── mspowerpoint_backend.py (3.3k tokens)
├── msword_backend.py (4.1k tokens)
├── pdf_backend.py (400 tokens)
├── pypdfium2_backend.py (1800 tokens)
├── xml/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── pubmed_backend.cpython-310.pyc (omitted)
├── pubmed_backend.cpython-312.pyc (omitted)
├── uspto_backend.cpython-310.pyc (omitted)
├── uspto_backend.cpython-312.pyc (omitted)
├── pubmed_backend.py (4.1k tokens)
├── uspto_backend.py (14.1k tokens)
├── chunking/
├── __init__.py (100 tokens)
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── cli/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── main.cpython-310.pyc (omitted)
├── models.cpython-310.pyc (omitted)
├── tools.cpython-310.pyc (omitted)
├── main.py (3.3k tokens)
├── models.py (600 tokens)
├── tools.py (100 tokens)
├── datamodel/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── base_models.cpython-310.pyc (omitted)
├── base_models.cpython-312.pyc (omitted)
├── document.cpython-310.pyc (omitted)
├── document.cpython-312.pyc (omitted)
├── pipeline_options.cpython-310.pyc (omitted)
├── pipeline_options.cpython-312.pyc (omitted)
├── settings.cpython-310.pyc (omitted)
├── settings.cpython-312.pyc (omitted)
├── base_models.py (1400 tokens)
├── document.py (2.7k tokens)
├── pipeline_options.py (1900 tokens)
├── settings.py (400 tokens)
├── document_converter.py (2.6k tokens)
├── exceptions.py
├── models/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── base_model.cpython-310.pyc (omitted)
├── base_model.cpython-312.pyc (omitted)
├── base_ocr_model.cpython-310.pyc (omitted)
├── base_ocr_model.cpython-312.pyc (omitted)
├── code_formula_model.cpython-310.pyc (omitted)
├── code_formula_model.cpython-312.pyc (omitted)
├── document_picture_classifier.cpython-310.pyc (omitted)
├── document_picture_classifier.cpython-312.pyc (omitted)
├── ds_glm_model.cpython-310.pyc (omitted)
├── ds_glm_model.cpython-312.pyc (omitted)
├── easyocr_model.cpython-310.pyc (omitted)
├── easyocr_model.cpython-312.pyc (omitted)
├── layout_model.cpython-310.pyc (omitted)
├── layout_model.cpython-312.pyc (omitted)
├── ocr_mac_model.cpython-310.pyc (omitted)
├── ocr_mac_model.cpython-312.pyc (omitted)
├── page_assemble_model.cpython-310.pyc (omitted)
├── page_assemble_model.cpython-312.pyc (omitted)
├── page_preprocessing_model.cpython-310.pyc (omitted)
├── page_preprocessing_model.cpython-312.pyc (omitted)
├── picture_description_api_model.cpython-310.pyc (omitted)
├── picture_description_api_model.cpython-312.pyc (omitted)
├── picture_description_base_model.cpython-310.pyc (omitted)
├── picture_description_base_model.cpython-312.pyc (omitted)
├── picture_description_vlm_model.cpython-310.pyc (omitted)
├── picture_description_vlm_model.cpython-312.pyc (omitted)
├── rapid_ocr_model.cpython-310.pyc (omitted)
├── rapid_ocr_model.cpython-312.pyc (omitted)
├── table_structure_model.cpython-310.pyc (omitted)
├── table_structure_model.cpython-312.pyc (omitted)
├── tesseract_ocr_cli_model.cpython-310.pyc (omitted)
├── tesseract_ocr_cli_model.cpython-312.pyc (omitted)
├── tesseract_ocr_model.cpython-310.pyc (omitted)
├── tesseract_ocr_model.cpython-312.pyc (omitted)
├── base_model.py (500 tokens)
├── base_ocr_model.py (1400 tokens)
├── code_formula_model.py (1700 tokens)
├── document_picture_classifier.py (1200 tokens)
├── ds_glm_model.py (3k tokens)
├── easyocr_model.py (1400 tokens)
├── layout_model.py (1600 tokens)
├── ocr_mac_model.py (900 tokens)
├── page_assemble_model.py (1200 tokens)
├── page_preprocessing_model.py (600 tokens)
├── picture_description_api_model.py (600 tokens)
├── picture_description_base_model.py (400 tokens)
├── picture_description_vlm_model.py (700 tokens)
├── rapid_ocr_model.py (1000 tokens)
├── table_structure_model.py (2.2k tokens)
├── tesseract_ocr_cli_model.py (1900 tokens)
├── tesseract_ocr_model.py (1700 tokens)
├── pipeline/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── base_pipeline.cpython-310.pyc (omitted)
├── base_pipeline.cpython-312.pyc (omitted)
├── simple_pipeline.cpython-310.pyc (omitted)
├── simple_pipeline.cpython-312.pyc (omitted)
├── standard_pdf_pipeline.cpython-310.pyc (omitted)
├── standard_pdf_pipeline.cpython-312.pyc (omitted)
├── base_pipeline.py (1700 tokens)
├── simple_pipeline.py (500 tokens)
├── standard_pdf_pipeline.py (2.5k tokens)
├── py.typed
├── utils/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── accelerator_utils.cpython-310.pyc (omitted)
├── accelerator_utils.cpython-312.pyc (omitted)
├── export.cpython-310.pyc (omitted)
├── glm_utils.cpython-310.pyc (omitted)
├── glm_utils.cpython-312.pyc (omitted)
├── layout_postprocessor.cpython-310.pyc (omitted)
├── layout_postprocessor.cpython-312.pyc (omitted)
├── model_downloader.cpython-310.pyc (omitted)
├── model_downloader.cpython-312.pyc (omitted)
├── ocr_utils.cpython-310.pyc (omitted)
├── ocr_utils.cpython-312.pyc (omitted)
├── profiling.cpython-310.pyc (omitted)
├── profiling.cpython-312.pyc (omitted)
├── utils.cpython-310.pyc (omitted)
├── utils.cpython-312.pyc (omitted)
├── visualization.cpython-310.pyc (omitted)
├── visualization.cpython-312.pyc (omitted)
├── accelerator_utils.py (300 tokens)
├── export.py (900 tokens)
├── glm_utils.py (2.5k tokens)
├── layout_postprocessor.py (4.9k tokens)
├── model_downloader.py (600 tokens)
├── ocr_utils.py (100 tokens)
├── profiling.py (400 tokens)
├── utils.py (400 tokens)
├── visualization.py (500 tokens)
├── utils/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── ablation_utils.cpython-310.pyc (omitted)
├── ablation_utils.cpython-312.pyc (omitted)
├── critic_utils.cpython-310.pyc (omitted)
├── critic_utils.cpython-312.pyc (omitted)
├── poster_eval_utils.cpython-310.pyc (omitted)
├── poster_eval_utils.cpython-312.pyc (omitted)
├── pptx_utils.cpython-310.pyc (omitted)
├── pptx_utils.cpython-312.pyc (omitted)
├── wei_utils.cpython-310.pyc (omitted)
├── wei_utils.cpython-312.pyc (omitted)
├── ablation_utils.py (500 tokens)
├── critic_utils.py (1100 tokens)
├── poster_eval_utils.py (8.7k tokens)
├── pptx_utils.py (14.7k tokens)
├── prompt_templates/
├── LLM_gen_HTML.yaml (300 tokens)
├── ablation_no_tree_layout.yaml (800 tokens)
├── actor_editor_agent.yaml (300 tokens)
├── actor_layout_hierarchy_2.yaml (500 tokens)
├── aesthetic_element_judge copy.yaml (300 tokens)
├── aesthetic_element_judge.yaml (400 tokens)
├── aesthetic_engagement_judge copy.yaml (400 tokens)
├── aesthetic_engagement_judge.yaml (400 tokens)
├── aesthetic_layout_judge copy.yaml (400 tokens)
├── aesthetic_layout_judge.yaml (400 tokens)
├── answer_question_from_image.yaml (500 tokens)
├── answer_question_from_text.yaml (600 tokens)
├── answer_question_from_text_no_ref.yaml (300 tokens)
├── bullet_point_agent.yaml (1000 tokens)
├── content_filler_agent.yaml (400 tokens)
├── critic_layout_hierarchy_1.yaml (300 tokens)
├── critic_overlap_agent.yaml (400 tokens)
├── critic_overlap_agent_v2.yaml (200 tokens)
├── critic_overlap_agent_v3.yaml (300 tokens)
├── critic_overlap_agent_v3_short.yaml (200 tokens)
├── generate_question_detail.yaml (700 tokens)
├── generate_question_understanding.yaml (600 tokens)
├── image_captioner.yaml (100 tokens)
├── image_table_filter_agent.yaml (600 tokens)
├── information_content_judge.yaml (1100 tokens)
├── information_logic_judge.yaml (800 tokens)
├── information_low_level_judge.yaml (600 tokens)
├── layout_agent.yaml (400 tokens)
├── layout_agent_init.yaml (400 tokens)
├── layout_agent_init_parallel.yaml (500 tokens)
├── layout_agent_new_section.yaml (500 tokens)
├── layout_agent_new_section_parallel.yaml (500 tokens)
├── poster_content_agent.yaml (700 tokens)
├── poster_planner_new.yaml (4.2k tokens)
├── poster_planner_new_v2.yaml (700 tokens)
├── poster_title_agent.yaml (400 tokens)
├── poster_title_agent_easy.yaml (300 tokens)
├── style_agent.yaml (500 tokens)
├── theme_agent_section.yaml (400 tokens)
├── theme_agent_title.yaml (300 tokens)
├── theme_templates/
├── theme_background.txt (200 tokens)
├── theme_section_body.txt (300 tokens)
├── theme_section_border.txt (200 tokens)
├── theme_section_title.txt (200 tokens)
├── theme_title_author.txt (200 tokens)
├── theme_title_author_border.txt (200 tokens)
├── prompt_utils.py
├── prompts/
├── ask_category.txt (100 tokens)
├── caption.txt (100 tokens)
├── category_split.txt (200 tokens)
├── content_induct.txt (200 tokens)
├── document_refine.txt (400 tokens)
├── gen_poster_raw_content.txt (400 tokens)
├── gen_poster_raw_content_v2.txt (400 tokens)
├── gen_theme.txt (500 tokens)
├── ppteval_coherence.txt (300 tokens)
├── ppteval_content.txt (300 tokens)
├── ppteval_describe_content.txt (100 tokens)
├── ppteval_describe_style.txt (100 tokens)
├── ppteval_extract.txt (100 tokens)
├── ppteval_style.txt (300 tokens)
├── src/
├── __init__.py
├── __pycache__/
├── __init__.cpython-310.pyc (omitted)
├── __init__.cpython-312.pyc (omitted)
├── model_utils.cpython-310.pyc (omitted)
├── model_utils.cpython-312.pyc (omitted)
├── presentation.cpython-310.pyc (omitted)
├── presentation.cpython-312.pyc (omitted)
├── utils.cpython-310.pyc (omitted)
├── utils.cpython-312.pyc (omitted)
├── apis.py (2.6k tokens)
├── experiment/
├── ablation.py (1300 tokens)
├── baseline_docpres.py (1700 tokens)
├── baseline_kctv.py (900 tokens)
├── crawler.py (2.6k tokens)
├── evals.py (2000 tokens)
├── experiments.py (1100 tokens)
├── preprocess.py (1900 tokens)
├── rebuild.py (500 tokens)
├── requirements.txt
├── statistic.py (1100 tokens)
├── induct.py (1600 tokens)
├── llms.py (3k tokens)
├── model_utils.py (1800 tokens)
├── multimodal.py (800 tokens)
├── pptgen.py (3.3k tokens)
├── presentation.py (8.1k tokens)
├── utils.py (2.1k tokens)
├── wei_utils.py (10.1k tokens)
├── prompt/
├── answer_question_from_video.yaml (400 tokens)
├── content_sim_score.txt (600 tokens)
├── ip_qa.txt (100 tokens)
├── ip_qa_find_human.txt (100 tokens)
├── which_is_better.txt (200 tokens)
├── requirements.txt (2.5k tokens)
├── pipeline.py (1900 tokens)
├── pipeline_light.py (1700 tokens)
├── prompts/
├── select_proposal.txt (200 tokens)
├── slide_beamer_correct.txt (100 tokens)
├── slide_beamer_prompt.txt (700 tokens)
├── slide_subtitle_cursor_prompt.txt (200 tokens)
├── requirements.txt
├── slide_code_gen_select_improvement.py (4.9k tokens)
├── speech_gen.py (500 tokens)
├── subtitle_cursor_prompt_gen.py (300 tokens)
├── subtitle_render.py (400 tokens)
├── talking_gen.py (500 tokens)
├── wei_utils.py (1500 tokens)
```
## /README-CN.md
# Paper2Video
<p align="right">
<a href="./README.md">English</a> | <b>简体中文</b>
</p>
<p align="center">
<b>Paper2Video: 从学术论文自动生成演讲视频</b>
<br>
<p align="center">
<a href="https://zeyu-zhu.github.io/webpage/">Zeyu Zhu*</a>,
<a href="https://qhlin.me/">Kevin Qinghong Lin*</a>,
<a href="https://scholar.google.com/citations?user=h1-3lSoAAAAJ&hl=en">Mike Zheng Shou</a> <br>
新加坡国立大学 Show Lab
</p>
<p align="center">
<a href="https://arxiv.org/abs/2510.05096">📄 论文</a> |
<a href="https://huggingface.co/papers/2510.05096">🤗 Daily Paper</a> |
<a href="https://huggingface.co/datasets/ZaynZhu/Paper2Video">📊 数据集</a> |
<a href="https://showlab.github.io/Paper2Video/">🌐 项目主页</a> |
<a href="https://x.com/KevinQHLin/status/1976105129146257542">💬 推特</a>
</p>
- **输入:** 一篇论文 ➕ 一张图像 ➕ 一段音频
| 论文 | 图像 | 音频 |
|--------|--------|--------|
| <img src="https://github.com/showlab/Paper2Video/blob/page/assets/hinton/paper.png" width="180"/><br>[🔗 论文链接](https://arxiv.org/pdf/1509.01626) | <img src="https://github.com/showlab/Paper2Video/blob/page/assets/hinton/hinton_head.jpeg" width="180"/> <br>Hinton的图像| <img src="assets/sound.png" width="180"/><br>[🔗 音频样本](https://github.com/showlab/Paper2Video/blob/page/assets/hinton/ref_audio_10.wav) |
- **输出:** 演讲视频
https://github.com/user-attachments/assets/39221a9a-48cb-4e20-9d1c-080a5d8379c4
查看更多生成结果 [🌐 project page](https://showlab.github.io/Paper2Video/).
## 🔥 Update
**我们欢迎任何贡献！**
- [x] [2025.10.15] 我们更新了一个没有talking-head的新版本，以便快速生成！
- [x] [2025.10.11] 我们的工作在[YC Hacker News](https://news.ycombinator.com/item?id=45553701)上受到关注.
- [x] [2025.10.9] 感谢AK在[Twitter](https://x.com/_akhaliq/status/1976099830004072849)上分享我们的工作!
- [x] [2025.10.9] 我们的工作被 [Medium](https://medium.com/@dataism/how-ai-learned-to-make-scientific-videos-from-slides-to-a-talking-head-0d807e491b27)报道.
- [x] [2025.10.8] 下方查看我们的demo视频!
- [x] [2025.10.7] 我们发布了 [Arxiv 论文](https://arxiv.org/abs/2510.05096).
- [x] [2025.10.6] 我们发布了 [代码](https://github.com/showlab/Paper2Video) and [数据集](https://huggingface.co/datasets/ZaynZhu/Paper2Video).
- [x] [2025.9.28] Paper2Video 已经被 **Scaling Environments for Agents Workshop([SEA](https://sea-workshop.github.io/)) at NeurIPS 2025** 接受.
https://github.com/user-attachments/assets/a655e3c7-9d76-4c48-b946-1068fdb6cdd9
---
### Table of Contents
- [🌟 项目总览](#-项目总览)
- [🚀 快速上手: PaperTalker](#-快速上手-PaperTalker)
- [1. 环境配置](#1-环境配置)
- [2. 大语言模型配置](#2-大语言模型配置)
- [3. 推理](#3-推理)
- [📊 评价指标: Paper2Video](#-评价指标-Paper2Video)
- [😼 乐趣: Paper2Video 生成 Paper2Video 演讲视频](#-乐趣-Paper2Video生成Paper2Video演讲视频)
- [🙏 致谢](#-致谢)
- [📌 引用](#-引用)
---
## 🌟 项目总览
<p align="center">
<img src="assets/teaser.png" alt="Overview" width="100%">
</p>
这项工作解决了学术演讲的两个核心问题:
- **左边: 如何根据论文制作学术演讲?**
*PaperTalker* — 集成**幻灯片**、**字幕**、**光标**、**语音合成**和**演讲者视频渲染**的多智能体。
- **右边: 如何评估学术演讲视频?**
*Paper2Video* — 一个具有精心设计的指标来评估演示质量的基准。
---
## 🚀 尝试 PaperTalker 为你的论文制作演讲视频 !
<p align="center">
<img src="assets/method.png" alt="Approach" width="100%">
</p>
### 1. 环境配置
准备Python环境:
```bash
cd src
conda create -n p2v python=3.10
conda activate p2v
pip install -r requirements.txt
conda install -c conda-forge tectonic
````
**[可选] 如果您不需要数字人展示，请 [跳过](#2-大语言模型配置) 此部分。**
下载所依赖代码，并按照[Hallo2](https://github.com/fudan-generative-vision/hallo2)中的说明下载模型权重。
```bash
git clone https://github.com/fudan-generative-vision/hallo2.git
```
您需要**单独准备用于 talking-head generation 的环境**，以避免潜在的软件包冲突，请参考<a href="git clone https://github.com/fudan-generative-vision/hallo2.git">Hallo2</a>。安装完成后，使用 `which python` 命令获取 Python 环境路径。
```bash
cd hallo2
conda create -n hallo python=3.10
conda activate hallo
pip install -r requirements.txt
```
### 2. 大语言模型配置
在终端配置您的**API 凭证**:
```bash
export GEMINI_API_KEY="your_gemini_key_here"
export OPENAI_API_KEY="your_openai_key_here"
```
最佳实践是针对 LLM 和 VLM 使用 **GPT4.1** 或 **Gemini2.5-Pro**。我们也支持本地部署开源模型（例如 Qwen），详情请参阅 <a href="https://github.com/Paper2Poster/Paper2Poster.git">Paper2Poster</a>。
### 3. 推理
脚本 `pipeline.py` 提供了一个自动化的学术演示视频生成流程。它以 **LaTeX 论文素材** 和 **参考图像/音频** 作为输入，并经过多个子模块（幻灯片 → 字幕 → 语音 → 光标 → 头部特写）生成完整的演示视频。⚡ 运行此流程的最低推荐 GPU 为 **NVIDIA A6000**，显存 48G。
#### 示例用法
运行以下命令启动快速生成（**不包含数字人生成**）：
```bash
python pipeline_light.py \
--model_name_t gpt-4.1 \
--model_name_v gpt-4.1 \
--result_dir /path/to/output \
--paper_latex_root /path/to/latex_proj \
--ref_img /path/to/ref_img.png \
--ref_audio /path/to/ref_audio.wav \
--gpu_list [0,1,2,3,4,5,6,7]
```
运行以下命令来启动完整生成（**包含数字人生成**）：
```bash
python pipeline.py \
--model_name_t gpt-4.1 \
--model_name_v gpt-4.1 \
--model_name_talking hallo2 \
--result_dir /path/to/output \
--paper_latex_root /path/to/latex_proj \
--ref_img /path/to/ref_img.png \
--ref_audio /path/to/ref_audio.wav \
--talking_head_env /path/to/hallo2_env \
--gpu_list [0,1,2,3,4,5,6,7]
```
| 参数名 | 类型 | 默认值 | 说明 |
|----------|------|---------|-------------|
| `--model_name_t` | `str` | `gpt-4.1` | 文本大语言模型（LLM） |
| `--model_name_v` | `str` | `gpt-4.1` | 视觉语言模型（VLM） |
| `--model_name_talking` | `str` | `hallo2` | Talking Head 模型。目前仅支持 **hallo2** |
| `--result_dir` | `str` | `/path/to/output` | 输出目录（包括幻灯片、字幕、视频等） |
| `--paper_latex_root` | `str` | `/path/to/latex_proj` | 论文 LaTeX 项目的根目录 |
| `--ref_img` | `str` | `/path/to/ref_img.png` | 参考图像（必须为**正方形**人像） |
| `--ref_audio` | `str` | `/path/to/ref_audio.wav` | 参考音频（建议时长约为 10 秒） |
| `--ref_text` | `str` | `None` | 可选参考文本（用于字幕风格指导） |
| `--beamer_templete_prompt` | `str` | `None` | 可选参考文本（用于幻灯片风格指导） |
| `--gpu_list` | `list[int]` | `""` | GPU 列表，用于并行执行（适用于**光标生成**与 **Talking Head 渲染**） |
| `--if_tree_search` | `bool` | `True` | 是否启用树搜索（用于幻灯片布局优化） |
| `--stage` | `str` | `"[0]"` | 需要运行的阶段（例如 `[0]` 表示完整流程，`[1,2,3]` 表示部分阶段） |
| `--talking_head_env` | `str` | `/path/to/hallo2_env` | Talking Head 生成的 Python 环境路径 |
---
## 📊 评价指标: Paper2Video
<p align="center">
<img src="assets/metrics.png" alt="Metrics" width="100%">
</p>
与自然视频生成不同，学术演示视频发挥着高度专业化的作用：它们不仅关乎视觉保真度，更关乎**学术交流**。这使得直接应用视频合成中的传统指标（例如 FVD、IS 或基于 CLIP 的相似度）变得困难。相反，它们的价值在于它们如何有效地**传播研究成果**并**提升学术知名度**。从这个角度来看，我们认为，评判高质量的学术演示视频应该从两个互补的维度进行评判：
#### 对于观众
- 视频应**忠实传达论文的核心思想**。
- 视频应**易于不同受众观看**。
#### 对于作者
- 视频应**突出作者的智力贡献和身份**。
- 视频应**提升作品的知名度和影响力**。
为了实现这些目标，我们引入了专门为学术演示视频设计的评估指标：Meta Similarity, PresentArena, PresentQuiz, IP Memory.
### 运行评价
- 准备环境：
```bash
cd src/evaluation
conda create -n p2v_e python=3.10
conda activate p2v_e
pip install -r requirements.txt
```
- 对于 Meta Similarity 和 PresentArena：
```bash
python MetaSim_audio.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
python MetaSim_content.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
```bash
python PresentArena.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
- 对于**PresentQuiz**，首先基于论文生成问题并使用 Gemini 进行评估：
```bash
cd PresentQuiz
python create_paper_questions.py ----paper_folder /path/to/data
python PresentQuiz.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
- 对于**IP Memory**，首先从生成的视频中生成问题对，然后使用 Gemini 进行评估：
```bash
cd IPMemory
python construct.py
python ip_qa.py
```
更多详情请查看代码！
👉 Paper2Video 数据集可在以下网址获取：
[HuggingFace](https://huggingface.co/datasets/ZaynZhu/Paper2Video)
---
## 😼 乐趣: Paper2Video 生成 Paper2Video 演讲视频
查看 **Paper2Video 生成 Paper2Video 演讲视频**:
https://github.com/user-attachments/assets/ff58f4d8-8376-4e12-b967-711118adf3c4
## 🙏 致谢
* 数据集中演示视频的来源是 SlideLive 和 YouTube。
* 感谢所有为制作演示视频付出辛勤努力的作者！
* 感谢 [CAMEL](https://github.com/camel-ai/camel) 开源了组织良好的多智能体框架代码库。
* 感谢 [Hallo2](https://github.com/fudan-generative-vision/hallo2.git) 和 [Paper2Poster](https://github.com/Paper2Poster/Paper2Poster.git) 作者开源代码。
* 感谢 [Wei Jia](https://github.com/weeadd) 在数据收集和baselines实现方面所做的努力。我们也感谢所有参与用户调研的参与者。
* 感谢所有 **Show Lab @ NUS** 成员的支持！
---
## 📌 引用
如果我们的工作对您有帮助，欢迎引用我们的工作：
```bibtex
@misc{paper2video,
title={Paper2Video: Automatic Video Generation from Scientific Papers},
author={Zeyu Zhu and Kevin Qinghong Lin and Mike Zheng Shou},
year={2025},
eprint={2510.05096},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.05096},
}
```
## /README.md
# Paper2Video
<p align="right">
<b>English</b> | <a href="./README-CN.md">简体中文</a>
</p>
<p align="center">
<b>Paper2Video: Automatic Video Generation from Scientific Papers</b>
<br>
从学术论文自动生成演讲视频
</p>
<p align="center">
<a href="https://zeyu-zhu.github.io/webpage/">Zeyu Zhu*</a>,
<a href="https://qhlin.me/">Kevin Qinghong Lin*</a>,
<a href="https://scholar.google.com/citations?user=h1-3lSoAAAAJ&hl=en">Mike Zheng Shou</a> <br>
Show Lab, National University of Singapore
</p>
<p align="center">
<a href="https://arxiv.org/abs/2510.05096">📄 Paper</a> |
<a href="https://huggingface.co/papers/2510.05096">🤗 Daily Paper</a> |
<a href="https://huggingface.co/datasets/ZaynZhu/Paper2Video">📊 Dataset</a> |
<a href="https://showlab.github.io/Paper2Video/">🌐 Project Website</a> |
<a href="https://x.com/KevinQHLin/status/1976105129146257542">💬 X (Twitter)</a>
</p>
- **Input:** a paper ➕ an image ➕ an audio
| Paper | Image | Audio |
|--------|--------|--------|
| <img src="https://github.com/showlab/Paper2Video/blob/page/assets/hinton/paper.png" width="180"/><br>[🔗 Paper link](https://arxiv.org/pdf/1509.01626) | <img src="https://github.com/showlab/Paper2Video/blob/page/assets/hinton/hinton_head.jpeg" width="180"/> <br>Hinton's photo| <img src="assets/sound.png" width="180"/><br>[🔗 Audio sample](https://github.com/showlab/Paper2Video/blob/page/assets/hinton/ref_audio_10.wav) |
- **Output:** a presentation video
https://github.com/user-attachments/assets/39221a9a-48cb-4e20-9d1c-080a5d8379c4
Check out more examples at [🌐 project page](https://showlab.github.io/Paper2Video/).
## 🔥 Update
**Any contributions are welcome!**
- [x] [2025.10.15] We update a new version without talking-head for fast generation!
- [x] [2025.10.11] Our work receives attention on [YC Hacker News](https://news.ycombinator.com/item?id=45553701).
- [x] [2025.10.9] Thanks AK for sharing our work on [Twitter](https://x.com/_akhaliq/status/1976099830004072849)!
- [x] [2025.10.9] Our work is reported by [Medium](https://medium.com/@dataism/how-ai-learned-to-make-scientific-videos-from-slides-to-a-talking-head-0d807e491b27).
- [x] [2025.10.8] Check out our demo video below!
- [x] [2025.10.7] We release the [arxiv paper](https://arxiv.org/abs/2510.05096).
- [x] [2025.10.6] We release the [code](https://github.com/showlab/Paper2Video) and [dataset](https://huggingface.co/datasets/ZaynZhu/Paper2Video).
- [x] [2025.9.28] Paper2Video has been accepted to the **Scaling Environments for Agents Workshop([SEA](https://sea-workshop.github.io/)) at NeurIPS 2025**.
https://github.com/user-attachments/assets/a655e3c7-9d76-4c48-b946-1068fdb6cdd9
---
### Table of Contents
- [🌟 Overview](#-overview)
- [🚀 Quick Start: PaperTalker](#-try-papertalker-for-your-paper-)
- [1. Requirements](#1-requirements)
- [2. Configure LLMs](#2-configure-llms)
- [3. Inference](#3-inference)
- [📊 Evaluation: Paper2Video](#-evaluation-paper2video)
- [😼 Fun: Paper2Video for Paper2Video](#-fun-paper2video-for-paper2video)
- [🙏 Acknowledgements](#-acknowledgements)
- [📌 Citation](#-citation)
---
## 🌟 Overview
<p align="center">
<img src="assets/teaser.png" alt="Overview" width="100%">
</p>
This work solves two core problems for academic presentations:
- **Left: How to create a presentation video from a paper?**
*PaperTalker* — an agent that integrates **slides**, **subtitling**, **cursor grounding**, **speech synthesis**, and **talking-head video rendering**.
- **Right: How to evaluate a presentation video?**
*Paper2Video* — a benchmark with well-designed metrics to evaluate presentation quality.
---
## 🚀 Try PaperTalker for your Paper!
<p align="center">
<img src="assets/method.png" alt="Approach" width="100%">
</p>
### 1. Requirements
Prepare the environment:
```bash
cd src
conda create -n p2v python=3.10
conda activate p2v
pip install -r requirements.txt
conda install -c conda-forge tectonic
```
**[Optional] [Skip](#2-configure-llms) this part if you do not need a human presenter.**
Download the dependent code and follow the instructions in **[Hallo2](https://github.com/fudan-generative-vision/hallo2)** to download the model weight.
```bash
git clone https://github.com/fudan-generative-vision/hallo2.git
```
You need to **prepare the environment separately for talking-head generation** to potential avoide package conflicts, please refer to <a href="git clone https://github.com/fudan-generative-vision/hallo2.git">Hallo2</a>. After installing, use `which python` to get the python environment path.
```bash
cd hallo2
conda create -n hallo python=3.10
conda activate hallo
pip install -r requirements.txt
```
### 2. Configure LLMs
Export your **API credentials**:
```bash
export GEMINI_API_KEY="your_gemini_key_here"
export OPENAI_API_KEY="your_openai_key_here"
```
The best practice is to use **GPT4.1** or **Gemini2.5-Pro** for both LLM and VLMs. We also support locally deployed open-source model(e.g., Qwen), details please referring to <a href="https://github.com/Paper2Poster/Paper2Poster.git">Paper2Poster</a>.
### 3. Inference
The script `pipeline.py` provides an automated pipeline for generating academic presentation videos. It takes **LaTeX paper sources** together with **reference image/audio** as input, and goes through multiple sub-modules (Slides → Subtitles → Speech → Cursor → Talking Head) to produce a complete presentation video. ⚡ The minimum recommended GPU for running this pipeline is **NVIDIA A6000** with 48G.
#### Example Usage
Run the following command to launch a fast generation (**without talking-head generation**):
```bash
python pipeline_light.py \
--model_name_t gpt-4.1 \
--model_name_v gpt-4.1 \
--result_dir /path/to/output \
--paper_latex_root /path/to/latex_proj \
--ref_img /path/to/ref_img.png \
--ref_audio /path/to/ref_audio.wav \
--gpu_list [0,1,2,3,4,5,6,7]
```
Run the following command to launch a full generation (**with talking-head generation**):
```bash
python pipeline.py \
--model_name_t gpt-4.1 \
--model_name_v gpt-4.1 \
--model_name_talking hallo2 \
--result_dir /path/to/output \
--paper_latex_root /path/to/latex_proj \
--ref_img /path/to/ref_img.png \
--ref_audio /path/to/ref_audio.wav \
--talking_head_env /path/to/hallo2_env \
--gpu_list [0,1,2,3,4,5,6,7]
```
| Argument | Type | Default | Description |
|----------|------|---------|-------------|
| `--model_name_t` | `str` | `gpt-4.1` | LLM |
| `--model_name_v` | `str` | `gpt-4.1` | VLM |
| `--model_name_talking` | `str` | `hallo2` | Talking Head model. Currently only **hallo2** is supported |
| `--result_dir` | `str` | `/path/to/output` | Output directory (slides, subtitles, videos, etc.) |
| `--paper_latex_root` | `str` | `/path/to/latex_proj` | Root directory of the LaTeX paper project |
| `--ref_img` | `str` | `/path/to/ref_img.png` | Reference image (must be **square** portrait) |
| `--ref_audio` | `str` | `/path/to/ref_audio.wav` | Reference audio (recommended: ~10s) |
| `--ref_text` | `str` | `None` | Optional reference text (for style guidance for subtitles) |
| `--beamer_templete_prompt` | `str` | `None` | Optional reference text (for style guidance for slides) |
| `--gpu_list` | `list[int]` | `""` | GPU list for parallel execution (used in **cursor generation** and **Talking Head rendering**) |
| `--if_tree_search` | `bool` | `True` | Whether to enable tree search for slide layout refinement |
| `--stage` | `str` | `"[0]"` | Pipeline stages to run (e.g., `[0]` full pipeline, `[1,2,3]` partial stages) |
| `--talking_head_env` | `str` | `/path/to/hallo2_env` | python environment path for talking-head generation |
---
## 📊 Evaluation: Paper2Video
<p align="center">
<img src="assets/metrics.png" alt="Metrics" width="100%">
</p>
Unlike natural video generation, academic presentation videos serve a highly specialized role: they are not merely about visual fidelity but about **communicating scholarship**. This makes it difficult to directly apply conventional metrics from video synthesis(e.g., FVD, IS, or CLIP-based similarity). Instead, their value lies in how well they **disseminate research** and **amplify scholarly visibility**.From this perspective, we argue that a high-quality academic presentation video should be judged along two complementary dimensions:
#### For the Audience
- The video is expected to **faithfully convey the paper’s core ideas**.
- It should remain **accessible to diverse audiences**.
#### For the Author
- The video should **foreground the authors’ intellectual contribution and identity**.
- It should **enhance the work’s visibility and impact**.
To capture these goals, we introduce evaluation metrics specifically designed for academic presentation videos: Meta Similarity, PresentArena, PresentQuiz, IP Memory.
### Run Eval
- Prepare the environment:
```bash
cd src/evaluation
conda create -n p2v_e python=3.10
conda activate p2v_e
pip install -r requirements.txt
```
- For MetaSimilarity and PresentArena:
```bash
python MetaSim_audio.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
python MetaSim_content.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
```bash
python PresentArena.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
- For **PresentQuiz**, first generate questions from paper and eval using Gemini:
```bash
cd PresentQuiz
python create_paper_questions.py ----paper_folder /path/to/data
python PresentQuiz.py --r /path/to/result_dir --g /path/to/gt_dir --s /path/to/save_dir
```
- For **IP Memory**, first generate question pairs from generated videos and eval using Gemini:
```bash
cd IPMemory
python construct.py
python ip_qa.py
```
See the codes for more details!
👉 Paper2Video Benchmark is available at:
[HuggingFace](https://huggingface.co/datasets/ZaynZhu/Paper2Video)
---
## 😼 Fun: Paper2Video for Paper2Video
Check out **How Paper2Video for Paper2Video**:
https://github.com/user-attachments/assets/ff58f4d8-8376-4e12-b967-711118adf3c4
## 🙏 Acknowledgements
* The souces of the presentation videos are SlideLive and YouTuBe.
* We thank all the authors who spend a great effort to create presentation videos!
* We thank [CAMEL](https://github.com/camel-ai/camel) for open-source well-organized multi-agent framework codebase.
* We thank the authors of [Hallo2](https://github.com/fudan-generative-vision/hallo2.git) and [Paper2Poster](https://github.com/Paper2Poster/Paper2Poster.git) for their open-sourced codes.
* We thank [Wei Jia](https://github.com/weeadd) for his effort in collecting the data and implementing the baselines. We also thank all the participants involved in the human studies.
* We thank all the **Show Lab @ NUS** members for support!
---
## 📌 Citation
If you find our work useful, please cite:
```bibtex
@misc{paper2video,
title={Paper2Video: Automatic Video Generation from Scientific Papers},
author={Zeyu Zhu and Kevin Qinghong Lin and Mike Zheng Shou},
year={2025},
eprint={2510.05096},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2510.05096},
}
```
[](https://star-history.com/#showlab/Paper2Video&Date)
## /assets/demo/latex_proj/fancyhdr.sty
```sty path="/assets/demo/latex_proj/fancyhdr.sty"
% fancyhdr.sty version 3.2
% Fancy headers and footers for LaTeX.
% Piet van Oostrum,
% Dept of Computer and Information Sciences, University of Utrecht,
% Padualaan 14, P.O. Box 80.089, 3508 TB Utrecht, The Netherlands
% Telephone: +31 30 2532180. Email: piet@cs.uu.nl
% ========================================================================
% LICENCE:
% This file may be distributed under the terms of the LaTeX Project Public
% License, as described in lppl.txt in the base LaTeX distribution.
% Either version 1 or, at your option, any later version.
% ========================================================================
% MODIFICATION HISTORY:
% Sep 16, 1994
% version 1.4: Correction for use with \reversemargin
% Sep 29, 1994:
% version 1.5: Added the \iftopfloat, \ifbotfloat and \iffloatpage commands
% Oct 4, 1994:
% version 1.6: Reset single spacing in headers/footers for use with
% setspace.sty or doublespace.sty
% Oct 4, 1994:
% version 1.7: changed \let\@mkboth\markboth to
% \def\@mkboth{\protect\markboth} to make it more robust
% Dec 5, 1994:
% version 1.8: corrections for amsbook/amsart: define \@chapapp and (more
% importantly) use the \chapter/sectionmark definitions from ps@headings if
% they exist (which should be true for all standard classes).
% May 31, 1995:
% version 1.9: The proposed \renewcommand{\headrulewidth}{\iffloatpage...
% construction in the doc did not work properly with the fancyplain style.
% June 1, 1995:
% version 1.91: The definition of \@mkboth wasn't restored on subsequent
% \pagestyle{fancy}'s.
% June 1, 1995:
% version 1.92: The sequence \pagestyle{fancyplain} \pagestyle{plain}
% \pagestyle{fancy} would erroneously select the plain version.
% June 1, 1995:
% version 1.93: \fancypagestyle command added.
% Dec 11, 1995:
% version 1.94: suggested by Conrad Hughes <chughes@maths.tcd.ie>
% CJCH, Dec 11, 1995: added \footruleskip to allow control over footrule
% position (old hardcoded value of .3\normalbaselineskip is far too high
% when used with very small footer fonts).
% Jan 31, 1996:
% version 1.95: call \@normalsize in the reset code if that is defined,
% otherwise \normalsize.
% this is to solve a problem with ucthesis.cls, as this doesn't
% define \@currsize. Unfortunately for latex209 calling \normalsize doesn't
% work as this is optimized to do very little, so there \@normalsize should
% be called. Hopefully this code works for all versions of LaTeX known to
% mankind.
% April 25, 1996:
% version 1.96: initialize \headwidth to a magic (negative) value to catch
% most common cases that people change it before calling \pagestyle{fancy}.
% Note it can't be initialized when reading in this file, because
% \textwidth could be changed afterwards. This is quite probable.
% We also switch to \MakeUppercase rather than \uppercase and introduce a
% \nouppercase command for use in headers. and footers.
% May 3, 1996:
% version 1.97: Two changes:
% 1. Undo the change in version 1.8 (using the pagestyle{headings} defaults
% for the chapter and section marks. The current version of amsbook and
% amsart classes don't seem to need them anymore. Moreover the standard
% latex classes don't use \markboth if twoside isn't selected, and this is
% confusing as \leftmark doesn't work as expected.
% 2. include a call to \ps@empty in ps@@fancy. This is to solve a problem
% in the amsbook and amsart classes, that make global changes to \topskip,
% which are reset in \ps@empty. Hopefully this doesn't break other things.
% May 7, 1996:
% version 1.98:
% Added % after the line \def\nouppercase
% May 7, 1996:
% version 1.99: This is the alpha version of fancyhdr 2.0
% Introduced the new commands \fancyhead, \fancyfoot, and \fancyhf.
% Changed \headrulewidth, \footrulewidth, \footruleskip to
% macros rather than length parameters, In this way they can be
% conditionalized and they don't consume length registers. There is no need
% to have them as length registers unless you want to do calculations with
% them, which is unlikely. Note that this may make some uses of them
% incompatible (i.e. if you have a file that uses \setlength or \xxxx=)
% May 10, 1996:
% version 1.99a:
% Added a few more % signs
% May 10, 1996:
% version 1.99b:
% Changed the syntax of \f@nfor to be resistent to catcode changes of :=
% Removed the [1] from the defs of \lhead etc. because the parameter is
% consumed by the \@[xy]lhead etc. macros.
% June 24, 1997:
% version 1.99c:
% corrected \nouppercase to also include the protected form of \MakeUppercase
% \global added to manipulation of \headwidth.
% \iffootnote command added.
% Some comments added about \@fancyhead and \@fancyfoot.
% Aug 24, 1998
% version 1.99d
% Changed the default \ps@empty to \ps@@empty in order to allow
% \fancypagestyle{empty} redefinition.
% Oct 11, 2000
% version 2.0
% Added LPPL license clause.
%
% A check for \headheight is added. An errormessage is given (once) if the
% header is too large. Empty headers don't generate the error even if
% \headheight is very small or even 0pt.
% Warning added for the use of 'E' option when twoside option is not used.
% In this case the 'E' fields will never be used.
%
% Mar 10, 2002
% version 2.1beta
% New command: \fancyhfoffset[place]{length}
% defines offsets to be applied to the header/footer to let it stick into
% the margins (if length > 0).
% place is like in fancyhead, except that only E,O,L,R can be used.
% This replaces the old calculation based on \headwidth and the marginpar
% area.
% \headwidth will be dynamically calculated in the headers/footers when
% this is used.
%
% Mar 26, 2002
% version 2.1beta2
% \fancyhfoffset now also takes h,f as possible letters in the argument to
% allow the header and footer widths to be different.
% New commands \fancyheadoffset and \fancyfootoffset added comparable to
% \fancyhead and \fancyfoot.
% Errormessages and warnings have been made more informative.
%
% Dec 9, 2002
% version 2.1
% The defaults for \footrulewidth, \plainheadrulewidth and
% \plainfootrulewidth are changed from \z@skip to 0pt. In this way when
% someone inadvertantly uses \setlength to change any of these, the value
% of \z@skip will not be changed, rather an errormessage will be given.
% March 3, 2004
% Release of version 3.0
% Oct 7, 2004
% version 3.1
% Added '\endlinechar=13' to \fancy@reset to prevent problems with
% includegraphics in header when verbatiminput is active.
% March 22, 2005
% version 3.2
% reset \everypar (the real one) in \fancy@reset because spanish.ldf does
% strange things with \everypar between << and >>.
\def\ifancy@mpty#1{\def\temp@a{#1}\ifx\temp@a\@empty}
\def\fancy@def#1#2{\ifancy@mpty{#2}\fancy@gbl\def#1{\leavevmode}\else
\fancy@gbl\def#1{#2\strut}\fi}
\let\fancy@gbl\global
\def\@fancyerrmsg#1{%
\ifx\PackageError\undefined
\errmessage{#1}\else
\PackageError{Fancyhdr}{#1}{}\fi}
\def\@fancywarning#1{%
\ifx\PackageWarning\undefined
\errmessage{#1}\else
\PackageWarning{Fancyhdr}{#1}{}\fi}
% Usage: \@forc \var{charstring}{command to be executed for each char}
% This is similar to LaTeX's \@tfor, but expands the charstring.
\def\@forc#1#2#3{\expandafter\f@rc\expandafter#1\expandafter{#2}{#3}}
\def\f@rc#1#2#3{\def\temp@ty{#2}\ifx\@empty\temp@ty\else
\f@@rc#1#2\f@@rc{#3}\fi}
\def\f@@rc#1#2#3\f@@rc#4{\def#1{#2}#4\f@rc#1{#3}{#4}}
% Usage: \f@nfor\name:=list\do{body}
% Like LaTeX's \@for but an empty list is treated as a list with an empty
% element
\newcommand{\f@nfor}[3]{\edef\@fortmp{#2}%
\expandafter\@forloop#2,\@nil,\@nil\@@#1{#3}}
% Usage: \def@ult \cs{defaults}{argument}
% sets \cs to the characters from defaults appearing in argument
% or defaults if it would be empty. All characters are lowercased.
\newcommand\def@ult[3]{%
\edef\temp@a{\lowercase{\edef\noexpand\temp@a{#3}}}\temp@a
\def#1{}%
\@forc\tmpf@ra{#2}%
{\expandafter\if@in\tmpf@ra\temp@a{\edef#1{#1\tmpf@ra}}{}}%
\ifx\@empty#1\def#1{#2}\fi}
%
% \if@in <char><set><truecase><falsecase>
%
\newcommand{\if@in}[4]{%
\edef\temp@a{#2}\def\temp@b##1#1##2\temp@b{\def\temp@b{##1}}%
\expandafter\temp@b#2#1\temp@b\ifx\temp@a\temp@b #4\else #3\fi}
\newcommand{\fancyhead}{\@ifnextchar[{\f@ncyhf\fancyhead h}%
{\f@ncyhf\fancyhead h[]}}
\newcommand{\fancyfoot}{\@ifnextchar[{\f@ncyhf\fancyfoot f}%
{\f@ncyhf\fancyfoot f[]}}
\newcommand{\fancyhf}{\@ifnextchar[{\f@ncyhf\fancyhf{}}%
{\f@ncyhf\fancyhf{}[]}}
% New commands for offsets added
\newcommand{\fancyheadoffset}{\@ifnextchar[{\f@ncyhfoffs\fancyheadoffset h}%
{\f@ncyhfoffs\fancyheadoffset h[]}}
\newcommand{\fancyfootoffset}{\@ifnextchar[{\f@ncyhfoffs\fancyfootoffset f}%
{\f@ncyhfoffs\fancyfootoffset f[]}}
\newcommand{\fancyhfoffset}{\@ifnextchar[{\f@ncyhfoffs\fancyhfoffset{}}%
{\f@ncyhfoffs\fancyhfoffset{}[]}}
% The header and footer fields are stored in command sequences with
% names of the form: \f@ncy<x><y><z> with <x> for [eo], <y> from [lcr]
% and <z> from [hf].
\def\f@ncyhf#1#2[#3]#4{%
\def\temp@c{}%
\@forc\tmpf@ra{#3}%
{\expandafter\if@in\tmpf@ra{eolcrhf,EOLCRHF}%
{}{\edef\temp@c{\temp@c\tmpf@ra}}}%
\ifx\@empty\temp@c\else
\@fancyerrmsg{Illegal char `\temp@c' in \string#1 argument:
[#3]}%
\fi
\f@nfor\temp@c{#3}%
{\def@ult\f@@@eo{eo}\temp@c
\if@twoside\else
\if\f@@@eo e\@fancywarning
{\string#1's `E' option without twoside option is useless}\fi\fi
\def@ult\f@@@lcr{lcr}\temp@c
\def@ult\f@@@hf{hf}{#2\temp@c}%
\@forc\f@@eo\f@@@eo
{\@forc\f@@lcr\f@@@lcr
{\@forc\f@@hf\f@@@hf
{\expandafter\fancy@def\csname
f@ncy\f@@eo\f@@lcr\f@@hf\endcsname
{#4}}}}}}
\def\f@ncyhfoffs#1#2[#3]#4{%
\def\temp@c{}%
\@forc\tmpf@ra{#3}%
{\expandafter\if@in\tmpf@ra{eolrhf,EOLRHF}%
{}{\edef\temp@c{\temp@c\tmpf@ra}}}%
\ifx\@empty\temp@c\else
\@fancyerrmsg{Illegal char `\temp@c' in \string#1 argument:
[#3]}%
\fi
\f@nfor\temp@c{#3}%
{\def@ult\f@@@eo{eo}\temp@c
\if@twoside\else
\if\f@@@eo e\@fancywarning
{\string#1's `E' option without twoside option is useless}\fi\fi
\def@ult\f@@@lcr{lr}\temp@c
\def@ult\f@@@hf{hf}{#2\temp@c}%
\@forc\f@@eo\f@@@eo
{\@forc\f@@lcr\f@@@lcr
{\@forc\f@@hf\f@@@hf
{\expandafter\setlength\csname
f@ncyO@\f@@eo\f@@lcr\f@@hf\endcsname
{#4}}}}}%
\fancy@setoffs}
% Fancyheadings version 1 commands. These are more or less deprecated,
% but they continue to work.
\newcommand{\lhead}{\@ifnextchar[{\@xlhead}{\@ylhead}}
\def\@xlhead[#1]#2{\fancy@def\f@ncyelh{#1}\fancy@def\f@ncyolh{#2}}
\def\@ylhead#1{\fancy@def\f@ncyelh{#1}\fancy@def\f@ncyolh{#1}}
\newcommand{\chead}{\@ifnextchar[{\@xchead}{\@ychead}}
\def\@xchead[#1]#2{\fancy@def\f@ncyech{#1}\fancy@def\f@ncyoch{#2}}
\def\@ychead#1{\fancy@def\f@ncyech{#1}\fancy@def\f@ncyoch{#1}}
\newcommand{\rhead}{\@ifnextchar[{\@xrhead}{\@yrhead}}
\def\@xrhead[#1]#2{\fancy@def\f@ncyerh{#1}\fancy@def\f@ncyorh{#2}}
\def\@yrhead#1{\fancy@def\f@ncyerh{#1}\fancy@def\f@ncyorh{#1}}
\newcommand{\lfoot}{\@ifnextchar[{\@xlfoot}{\@ylfoot}}
\def\@xlfoot[#1]#2{\fancy@def\f@ncyelf{#1}\fancy@def\f@ncyolf{#2}}
\def\@ylfoot#1{\fancy@def\f@ncyelf{#1}\fancy@def\f@ncyolf{#1}}
\newcommand{\cfoot}{\@ifnextchar[{\@xcfoot}{\@ycfoot}}
\def\@xcfoot[#1]#2{\fancy@def\f@ncyecf{#1}\fancy@def\f@ncyocf{#2}}
\def\@ycfoot#1{\fancy@def\f@ncyecf{#1}\fancy@def\f@ncyocf{#1}}
\newcommand{\rfoot}{\@ifnextchar[{\@xrfoot}{\@yrfoot}}
\def\@xrfoot[#1]#2{\fancy@def\f@ncyerf{#1}\fancy@def\f@ncyorf{#2}}
\def\@yrfoot#1{\fancy@def\f@ncyerf{#1}\fancy@def\f@ncyorf{#1}}
\newlength{\fancy@headwidth}
\let\headwidth\fancy@headwidth
\newlength{\f@ncyO@elh}
\newlength{\f@ncyO@erh}
\newlength{\f@ncyO@olh}
\newlength{\f@ncyO@orh}
\newlength{\f@ncyO@elf}
\newlength{\f@ncyO@erf}
\newlength{\f@ncyO@olf}
\newlength{\f@ncyO@orf}
\newcommand{\headrulewidth}{0.4pt}
\newcommand{\footrulewidth}{0pt}
\newcommand{\footruleskip}{.3\normalbaselineskip}
% Fancyplain stuff shouldn't be used anymore (rather
% \fancypagestyle{plain} should be used), but it must be present for
% compatibility reasons.
\newcommand{\plainheadrulewidth}{0pt}
\newcommand{\plainfootrulewidth}{0pt}
\newif\if@fancyplain \@fancyplainfalse
\def\fancyplain#1#2{\if@fancyplain#1\else#2\fi}
\headwidth=-123456789sp %magic constant
% Command to reset various things in the headers:
% a.o. single spacing (taken from setspace.sty)
% and the catcode of ^^M (so that epsf files in the header work if a
% verbatim crosses a page boundary)
% It also defines a \nouppercase command that disables \uppercase and
% \Makeuppercase. It can only be used in the headers and footers.
\let\fnch@everypar\everypar% save real \everypar because of spanish.ldf
\def\fancy@reset{\fnch@everypar{}\restorecr\endlinechar=13
\def\baselinestretch{1}%
\def\nouppercase##1{{\let\uppercase\relax\let\MakeUppercase\relax
\expandafter\let\csname MakeUppercase \endcsname\relax##1}}%
\ifx\undefined\@newbaseline% NFSS not present; 2.09 or 2e
\ifx\@normalsize\undefined \normalsize % for ucthesis.cls
\else \@normalsize \fi
\else% NFSS (2.09) present
\@newbaseline%
\fi}
% Initialization of the head and foot text.
% The default values still contain \fancyplain for compatibility.
\fancyhf{} % clear all
% lefthead empty on ``plain'' pages, \rightmark on even, \leftmark on odd pages
% evenhead empty on ``plain'' pages, \leftmark on even, \rightmark on odd pages
\if@twoside
\fancyhead[el,or]{\fancyplain{}{\sl\rightmark}}
\fancyhead[er,ol]{\fancyplain{}{\sl\leftmark}}
\else
\fancyhead[l]{\fancyplain{}{\sl\rightmark}}
\fancyhead[r]{\fancyplain{}{\sl\leftmark}}
\fi
\fancyfoot[c]{\rm\thepage} % page number
% Use box 0 as a temp box and dimen 0 as temp dimen.
% This can be done, because this code will always
% be used inside another box, and therefore the changes are local.
\def\@fancyvbox#1#2{\setbox0\vbox{#2}\ifdim\ht0>#1\@fancywarning
{\string#1 is too small (\the#1): ^^J Make it at least \the\ht0.^^J
We now make it that large for the rest of the document.^^J
This may cause the page layout to be inconsistent, however\@gobble}%
\dimen0=#1\global\setlength{#1}{\ht0}\ht0=\dimen0\fi
\box0}
% Put together a header or footer given the left, center and
% right text, fillers at left and right and a rule.
% The \lap commands put the text into an hbox of zero size,
% so overlapping text does not generate an errormessage.
% These macros have 5 parameters:
% 1. LEFTSIDE BEARING % This determines at which side the header will stick
% out. When \fancyhfoffset is used this calculates \headwidth, otherwise
% it is \hss or \relax (after expansion).
% 2. \f@ncyolh, \f@ncyelh, \f@ncyolf or \f@ncyelf. This is the left component.
% 3. \f@ncyoch, \f@ncyech, \f@ncyocf or \f@ncyecf. This is the middle comp.
% 4. \f@ncyorh, \f@ncyerh, \f@ncyorf or \f@ncyerf. This is the right component.
% 5. RIGHTSIDE BEARING. This is always \relax or \hss (after expansion).
\def\@fancyhead#1#2#3#4#5{#1\hbox to\headwidth{\fancy@reset
\@fancyvbox\headheight{\hbox
{\rlap{\parbox[b]{\headwidth}{\raggedright#2}}\hfill
\parbox[b]{\headwidth}{\centering#3}\hfill
\llap{\parbox[b]{\headwidth}{\raggedleft#4}}}\headrule}}#5}
\def\@fancyfoot#1#2#3#4#5{#1\hbox to\headwidth{\fancy@reset
\@fancyvbox\footskip{\footrule
\hbox{\rlap{\parbox[t]{\headwidth}{\raggedright#2}}\hfill
\parbox[t]{\headwidth}{\centering#3}\hfill
\llap{\parbox[t]{\headwidth}{\raggedleft#4}}}}}#5}
\def\headrule{{\if@fancyplain\let\headrulewidth\plainheadrulewidth\fi
\hrule\@height\headrulewidth\@width\headwidth \vskip-\headrulewidth}}
\def\footrule{{\if@fancyplain\let\footrulewidth\plainfootrulewidth\fi
\vskip-\footruleskip\vskip-\footrulewidth
\hrule\@width\headwidth\@height\footrulewidth\vskip\footruleskip}}
\def\ps@fancy{%
\@ifundefined{@chapapp}{\let\@chapapp\chaptername}{}%for amsbook
%
% Define \MakeUppercase for old LaTeXen.
% Note: we used \def rather than \let, so that \let\uppercase\relax (from
% the version 1 documentation) will still work.
%
\@ifundefined{MakeUppercase}{\def\MakeUppercase{\uppercase}}{}%
\@ifundefined{chapter}{\def\sectionmark##1{\markboth
{\MakeUppercase{\ifnum \c@secnumdepth>\z@
\thesection\hskip 1em\relax \fi ##1}}{}}%
\def\subsectionmark##1{\markright {\ifnum \c@secnumdepth >\@ne
\thesubsection\hskip 1em\relax \fi ##1}}}%
{\def\chaptermark##1{\markboth {\MakeUppercase{\ifnum \c@secnumdepth>\m@ne
\@chapapp\ \thechapter. \ \fi ##1}}{}}%
\def\sectionmark##1{\markright{\MakeUppercase{\ifnum \c@secnumdepth >\z@
\thesection. \ \fi ##1}}}}%
%\csname ps@headings\endcsname % use \ps@headings defaults if they exist
\ps@@fancy
\gdef\ps@fancy{\@fancyplainfalse\ps@@fancy}%
% Initialize \headwidth if the user didn't
%
\ifdim\headwidth<0sp
%
% This catches the case that \headwidth hasn't been initialized and the
% case that the user added something to \headwidth in the expectation that
% it was initialized to \textwidth. We compensate this now. This loses if
% the user intended to multiply it by a factor. But that case is more
% likely done by saying something like \headwidth=1.2\textwidth.
% The doc says you have to change \headwidth after the first call to
% \pagestyle{fancy}. This code is just to catch the most common cases were
% that requirement is violated.
%
\global\advance\headwidth123456789sp\global\advance\headwidth\textwidth
\fi}
\def\ps@fancyplain{\ps@fancy \let\ps@plain\ps@plain@fancy}
\def\ps@plain@fancy{\@fancyplaintrue\ps@@fancy}
\let\ps@@empty\ps@empty
\def\ps@@fancy{%
\ps@@empty % This is for amsbook/amsart, which do strange things with \topskip
\def\@mkboth{\protect\markboth}%
\def\@oddhead{\@fancyhead\fancy@Oolh\f@ncyolh\f@ncyoch\f@ncyorh\fancy@Oorh}%
\def\@oddfoot{\@fancyfoot\fancy@Oolf\f@ncyolf\f@ncyocf\f@ncyorf\fancy@Oorf}%
\def\@evenhead{\@fancyhead\fancy@Oelh\f@ncyelh\f@ncyech\f@ncyerh\fancy@Oerh}%
\def\@evenfoot{\@fancyfoot\fancy@Oelf\f@ncyelf\f@ncyecf\f@ncyerf\fancy@Oerf}%
}
% Default definitions for compatibility mode:
% These cause the header/footer to take the defined \headwidth as width
% And to shift in the direction of the marginpar area
\def\fancy@Oolh{\if@reversemargin\hss\else\relax\fi}
\def\fancy@Oorh{\if@reversemargin\relax\else\hss\fi}
\let\fancy@Oelh\fancy@Oorh
\let\fancy@Oerh\fancy@Oolh
\let\fancy@Oolf\fancy@Oolh
\let\fancy@Oorf\fancy@Oorh
\let\fancy@Oelf\fancy@Oelh
\let\fancy@Oerf\fancy@Oerh
% New definitions for the use of \fancyhfoffset
% These calculate the \headwidth from \textwidth and the specified offsets.
\def\fancy@offsolh{\headwidth=\textwidth\advance\headwidth\f@ncyO@olh
\advance\headwidth\f@ncyO@orh\hskip-\f@ncyO@olh}
\def\fancy@offselh{\headwidth=\textwidth\advance\headwidth\f@ncyO@elh
\advance\headwidth\f@ncyO@erh\hskip-\f@ncyO@elh}
\def\fancy@offsolf{\headwidth=\textwidth\advance\headwidth\f@ncyO@olf
\advance\headwidth\f@ncyO@orf\hskip-\f@ncyO@olf}
\def\fancy@offself{\headwidth=\textwidth\advance\headwidth\f@ncyO@elf
\advance\headwidth\f@ncyO@erf\hskip-\f@ncyO@elf}
\def\fancy@setoffs{%
% Just in case \let\headwidth\textwidth was used
\fancy@gbl\let\headwidth\fancy@headwidth
\fancy@gbl\let\fancy@Oolh\fancy@offsolh
\fancy@gbl\let\fancy@Oelh\fancy@offselh
\fancy@gbl\let\fancy@Oorh\hss
\fancy@gbl\let\fancy@Oerh\hss
\fancy@gbl\let\fancy@Oolf\fancy@offsolf
\fancy@gbl\let\fancy@Oelf\fancy@offself
\fancy@gbl\let\fancy@Oorf\hss
\fancy@gbl\let\fancy@Oerf\hss}
\newif\iffootnote
\let\latex@makecol\@makecol
\def\@makecol{\ifvoid\footins\footnotetrue\else\footnotefalse\fi
\let\topfloat\@toplist\let\botfloat\@botlist\latex@makecol}
\def\iftopfloat#1#2{\ifx\topfloat\empty #2\else #1\fi}
\def\ifbotfloat#1#2{\ifx\botfloat\empty #2\else #1\fi}
\def\iffloatpage#1#2{\if@fcolmade #1\else #2\fi}
\newcommand{\fancypagestyle}[2]{%
\@namedef{ps@#1}{\let\fancy@gbl\relax#2\relax\ps@fancy}}
```
## /assets/demo/latex_proj/figure/data_stat.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/data_stat.pdf
## /assets/demo/latex_proj/figure/eval.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/eval.pdf
## /assets/demo/latex_proj/figure/human_evaluation_bar.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/human_evaluation_bar.pdf
## /assets/demo/latex_proj/figure/icon.png
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/icon.png
## /assets/demo/latex_proj/figure/logo.png
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/logo.png
## /assets/demo/latex_proj/figure/logo_.png
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/logo_.png
## /assets/demo/latex_proj/figure/mcts.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/mcts.pdf
## /assets/demo/latex_proj/figure/method.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/method.pdf
## /assets/demo/latex_proj/figure/paper_topics_wordcloud.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/paper_topics_wordcloud.pdf
## /assets/demo/latex_proj/figure/presenter.png
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/presenter.png
## /assets/demo/latex_proj/figure/slides_count_hist.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/slides_count_hist.pdf
## /assets/demo/latex_proj/figure/teaser.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/teaser.pdf
## /assets/demo/latex_proj/figure/tree_search.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/tree_search.pdf
## /assets/demo/latex_proj/figure/tree_search_vis.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/tree_search_vis.pdf
## /assets/demo/latex_proj/figure/video_length_hist.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/video_length_hist.pdf
## /assets/demo/latex_proj/figure/vis.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/vis.pdf
## /assets/demo/latex_proj/figure/visual.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/figure/visual.pdf
## /assets/demo/latex_proj/iclr2025_conference.bib
```bib path="/assets/demo/latex_proj/iclr2025_conference.bib"
@article{zheng2025pptagent,
title={Pptagent: Generating and evaluating presentations beyond text-to-slides},
author={Zheng, Hao and Guan, Xinyan and Kong, Hao and Zheng, Jia and Zhou, Weixiang and Lin, Hongyu and Lu, Yaojie and He, Ben and Han, Xianpei and Sun, Le},
journal={arXiv preprint arXiv:2501.03936},
year={2025}
}
@article{pang2025paper2poster,
title={Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers},
author={Pang, Wei and Lin, Kevin Qinghong and Jian, Xiangru and He, Xi and Torr, Philip},
journal={arXiv preprint arXiv:2505.21497},
year={2025}
}
@techreport{deepmind2025veo3,
title = {Veo 3 Technical Report},
author = {{DeepMind}},
year = {2025},
month = may,
institution = {DeepMind},
note = {Technical Report},
url = {https://storage.googleapis.com/deepmind-media/veo/Veo-3-Tech-Report.pdf}
}
@article{sun2021d2s,
title={D2S: Document-to-slide generation via query-based text summarization},
author={Sun, Edward and Hou, Yufang and Wang, Dakuo and Zhang, Yunfeng and Wang, Nancy XR},
journal={arXiv preprint arXiv:2105.03664},
year={2021}
}
@article{ma2025controllable,
title={Controllable video generation: A survey},
author={Ma, Yue and Feng, Kunyu and Hu, Zhongyuan and Wang, Xinyu and Wang, Yucheng and Zheng, Mingzhe and He, Xuanhua and Zhu, Chenyang and Liu, Hongyu and He, Yingqing and others},
journal={arXiv preprint arXiv:2507.16869},
year={2025}
}
@inproceedings{lin2025showui,
title={Showui: One vision-language-action model for gui visual agent},
author={Lin, Kevin Qinghong and Li, Linjie and Gao, Difei and Yang, Zhengyuan and Wu, Shiwei and Bai, Zechen and Lei, Stan Weixian and Wang, Lijuan and Shou, Mike Zheng},
booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
pages={19498--19508},
year={2025}
}
@article{qin2025ui,
title={Ui-tars: Pioneering automated gui interaction with native agents},
author={Qin, Yujia and Ye, Yining and Fang, Junjie and Wang, Haoming and Liang, Shihao and Tian, Shizuo and Zhang, Junda and Li, Jiahao and Li, Yunxin and Huang, Shijue and others},
journal={arXiv preprint arXiv:2501.12326},
year={2025}
}
@article{bain2023whisperx,
title={Whisperx: Time-accurate speech transcription of long-form audio},
author={Bain, Max and Huh, Jaesung and Han, Tengda and Zisserman, Andrew},
journal={arXiv preprint arXiv:2303.00747},
year={2023}
}
@article{chen2024f5,
title={F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching},
author={Chen, Yushen and Niu, Zhikang and Ma, Ziyang and Deng, Keqi and Wang, Chunhui and Zhao, Jian and Yu, Kai and Chen, Xie},
journal={arXiv preprint arXiv:2410.06885},
year={2024}
}
@article{cui2024hallo2,
title={Hallo2: Long-duration and high-resolution audio-driven portrait image animation},
author={Cui, Jiahao and Li, Hui and Yao, Yao and Zhu, Hao and Shang, Hanlin and Cheng, Kaihui and Zhou, Hang and Zhu, Siyu and Wang, Jingdong},
journal={arXiv preprint arXiv:2410.07718},
year={2024}
}
@inproceedings{rombach2022high,
title={High-resolution image synthesis with latent diffusion models},
author={Rombach, Robin and Blattmann, Andreas and Lorenz, Dominik and Esser, Patrick and Ommer, Bj{\"o}rn},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={10684--10695},
year={2022}
}
@article{wu2025automated,
title={Automated movie generation via multi-agent cot planning},
author={Wu, Weijia and Zhu, Zeyu and Shou, Mike Zheng},
journal={arXiv preprint arXiv:2503.07314},
year={2025}
}
@article{shi2025presentagent,
title={Presentagent: Multimodal agent for presentation video generation},
author={Shi, Jingwei and Zhang, Zeyu and Wu, Biao and Liang, Yanjie and Fang, Meng and Chen, Ling and Zhao, Yang},
journal={arXiv preprint arXiv:2507.04036},
year={2025}
}
@article{ai4research,
title={AI4Research: A Survey of Artificial Intelligence for Scientific Research},
author={Chen, Qiguang and Yang, Mingda and Qin, Libo and Liu, Jinhao and Yan, Zheng and Guan, Jiannan and Peng, Dengyun and Ji, Yiyan and Li, Hanjing and Hu, Mengkang and others},
journal={arXiv preprint arXiv:2507.01903},
year={2025}
}
@inproceedings{writing_ass,
title = "Automated Focused Feedback Generation for Scientific Writing Assistance",
author = "Chamoun, Eric and
Schlichtkrull, Michael and
Vlachos, Andreas",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.580/",
doi = "10.18653/v1/2024.findings-acl.580",
pages = "9742--9763",
abstract = "Scientific writing is a challenging task, particularly for novice researchers who often rely on feedback from experienced peers. Recent work has primarily focused on improving surface form and style rather than manuscript content. In this paper, we propose a novel task: automated focused feedback generation for scientific writing assistance. We present SWIF$^2$T: a Scientific WrIting Focused Feedback Tool. It is designed to generate specific, actionable and coherent comments, which identify weaknesses in a scientific paper and/or propose revisions to it. Our approach consists of four components - planner, investigator, reviewer and controller - leveraging multiple Large Language Models (LLMs) to implement them. We compile a dataset of 300 peer reviews citing weaknesses in scientific papers and conduct human evaluation. The results demonstrate the superiority in specificity, reading comprehension, and overall helpfulness of SWIF$^2$T{'}s feedback compared to other approaches. In our analysis, we also identified cases where automatically generated reviews were judged better than human ones, suggesting opportunities for integration of AI-generated feedback in scientific writing."
}
@article{sci_lit,
title={Knowledge navigator: Llm-guided browsing framework for exploratory search in scientific literature},
author={Katz, Uri and Levy, Mosh and Goldberg, Yoav},
journal={arXiv preprint arXiv:2408.15836},
year={2024}
}
@inproceedings{hu2024novachart,
title={Novachart: A large-scale dataset towards chart understanding and generation of multimodal large language models},
author={Hu, Linmei and Wang, Duokang and Pan, Yiming and Yu, Jifan and Shao, Yingxia and Feng, Chong and Nie, Liqiang},
booktitle={Proceedings of the 32nd ACM International Conference on Multimedia},
pages={3917--3925},
year={2024}
}
@article{fantasytalking,
title={Fantasytalking: Realistic talking portrait generation via coherent motion synthesis},
author={Wang, Mengchao and Wang, Qiang and Jiang, Fan and Fan, Yaqi and Zhang, Yunpeng and Qi, Yonggang and Zhao, Kun and Xu, Mu},
journal={arXiv preprint arXiv:2504.04842},
year={2025}
}
@article{tts-f5,
title={F5-tts: A fairytaler that fakes fluent and faithful speech with flow matching},
author={Chen, Yushen and Niu, Zhikang and Ma, Ziyang and Deng, Keqi and Wang, Chunhui and Zhao, Jian and Yu, Kai and Chen, Xie},
journal={arXiv preprint arXiv:2410.06885},
year={2024}
}
@article{audio_embedding,
author = {Mirco Ravanelli and Titouan Parcollet and Adel Moumen and Sylvain de Langen and Cem Subakan and Peter Plantinga and Yingzhi Wang and Pooneh Mousavi and Luca Della Libera and Artem Ploujnikov and Francesco Paissan and Davide Borra and Salah Zaiem and Zeyu Zhao and Shucong Zhang and Georgios Karakasidis and Sung-Lin Yeh and Pierre Champion and Aku Rouhe and Rudolf Braun and Florian Mai and Juan Zuluaga-Gomez and Seyed Mahed Mousavi and Andreas Nautsch and Ha Nguyen and Xuechen Liu and Sangeet Sagar and Jarod Duret and Salima Mdhaffar and Ga{{\"e}}lle Laperri{{\`e}}re and Mickael Rouvier and Renato De Mori and Yannick Est{{\`e}}ve},
title = {Open-Source Conversational AI with SpeechBrain 1.0},
journal = {Journal of Machine Learning Research},
year = {2024},
volume = {25},
number = {333},
url = {http://jmlr.org/papers/v25/24-0991.html}
}
@article{paper2code,
title={Paper2code: Automating code generation from scientific papers in machine learning},
author={Seo, Minju and Baek, Jinheon and Lee, Seongyun and Hwang, Sung Ju},
journal={arXiv preprint arXiv:2504.17192},
year={2025}
}
@inproceedings{wu2025moviebench,
title={Moviebench: A hierarchical movie level dataset for long video generation},
author={Wu, Weijia and Liu, Mingyu and Zhu, Zeyu and Xia, Xi and Feng, Haoen and Wang, Wen and Lin, Kevin Qinghong and Shen, Chunhua and Shou, Mike Zheng},
booktitle={Proceedings of the Computer Vision and Pattern Recognition Conference},
pages={28984--28994},
year={2025}
}
@inproceedings{vbench,
title={Vbench: Comprehensive benchmark suite for video generative models},
author={Huang, Ziqi and He, Yinan and Yu, Jiashuo and Zhang, Fan and Si, Chenyang and Jiang, Yuming and Zhang, Yuanhan and Wu, Tianxing and Jin, Qingyang and Chanpaisit, Nattapol and others},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={21807--21818},
year={2024}
}
@article{wan,
title={Wan: Open and advanced large-scale video generative models},
author={Wan, Team and Wang, Ang and Ai, Baole and Wen, Bin and Mao, Chaojie and Xie, Chen-Wei and Chen, Di and Yu, Feiwu and Zhao, Haiming and Yang, Jianxiao and others},
journal={arXiv preprint arXiv:2503.20314},
year={2025}
}
@inproceedings{camel,
title={CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society},
author={Li, Guohao and Hammoud, Hasan Abed Al Kader and Itani, Hani and Khizbullin, Dmitrii and Ghanem, Bernard},
booktitle={Thirty-seventh Conference on Neural Information Processing Systems},
year={2023}
}
@article{paperbench,
title={PaperBench: Evaluating AI's Ability to Replicate AI Research},
author={Starace, Giulio and Jaffe, Oliver and Sherburn, Dane and Aung, James and Chan, Jun Shern and Maksin, Leon and Dias, Rachel and Mays, Evan and Kinsella, Benjamin and Thompson, Wyatt and others},
journal={arXiv preprint arXiv:2504.01848},
year={2025}
}
@inproceedings{talking-head-1,
title={Flowvqtalker: High-quality emotional talking face generation through normalizing flow and quantization},
author={Tan, Shuai and Ji, Bin and Pan, Ye},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={26317--26327},
year={2024}
}
@inproceedings{talking-head-2,
title={Learning individual styles of conversational gesture},
author={Ginosar, Shiry and Bar, Amir and Kohavi, Gefen and Chan, Caroline and Owens, Andrew and Malik, Jitendra},
booktitle={Proceedings of the IEEE/CVF conference on computer vision and pattern recognition},
pages={3497--3506},
year={2019}
}
@inproceedings{evalcrafter,
title={Evalcrafter: Benchmarking and evaluating large video generation models},
author={Liu, Yaofang and Cun, Xiaodong and Liu, Xuebo and Wang, Xintao and Zhang, Yong and Chen, Haoxin and Liu, Yang and Zeng, Tieyong and Chan, Raymond and Shan, Ying},
booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition},
pages={22139--22149},
year={2024}
}
@article{vbench++,
title={Vbench++: Comprehensive and versatile benchmark suite for video generative models},
author={Huang, Ziqi and Zhang, Fan and Xu, Xiaojie and He, Yinan and Yu, Jiashuo and Dong, Ziyue and Ma, Qianli and Chanpaisit, Nattapol and Si, Chenyang and Jiang, Yuming and others},
journal={arXiv preprint arXiv:2411.13503},
year={2024}
}
@inproceedings{dasigi-etal,
title = "A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers",
author = "Dasigi, Pradeep and
Lo, Kyle and
Beltagy, Iz and
Cohan, Arman and
Smith, Noah A. and
Gardner, Matt",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.365/",
doi = "10.18653/v1/2021.naacl-main.365",
pages = "4599--4610",
abstract = "Readers of academic research papers often read with the goal of answering specific questions. Question Answering systems that can answer those questions can make consumption of the content much more efficient. However, building such tools requires data that reflect the difficulty of the task arising from complex reasoning about claims made in multiple parts of a paper. In contrast, existing information-seeking question answering datasets usually contain questions about generic factoid-type information. We therefore present Qasper, a dataset of 5049 questions over 1585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers. We find that existing models that do well on other QA tasks do not perform well on answering these questions, underperforming humans by at least 27 F1 points when answering them from entire papers, motivating further research in document-grounded, information-seeking QA, which our dataset is designed to facilitate."
}
@article{scireplicate,
title={Scireplicate-bench: Benchmarking llms in agent-driven algorithmic reproduction from research papers},
author={Xiang, Yanzheng and Yan, Hanqi and Ouyang, Shuyin and Gui, Lin and He, Yulan},
journal={arXiv preprint arXiv:2504.00255},
year={2025}
}
@article{scienceagentbench,
title={Scienceagentbench: Toward rigorous assessment of language agents for data-driven scientific discovery},
author={Chen, Ziru and Chen, Shijie and Ning, Yuting and Zhang, Qianheng and Wang, Boshi and Yu, Botao and Li, Yifei and Liao, Zeyi and Wei, Chen and Lu, Zitong and others},
journal={arXiv preprint arXiv:2410.05080},
year={2024}
}
@article{bixbench,
title={Bixbench: a comprehensive benchmark for llm-based agents in computational biology},
author={Mitchener, Ludovico and Laurent, Jon M and Tenmann, Benjamin and Narayanan, Siddharth and Wellawatte, Geemi P and White, Andrew and Sani, Lorenzo and Rodriques, Samuel G},
journal={arXiv preprint arXiv:2503.00096},
year={2025}
}
@article{Llm-srbench,
title={Llm-srbench: A new benchmark for scientific equation discovery with large language models},
author={Shojaee, Parshin and Nguyen, Ngoc-Hieu and Meidani, Kazem and Farimani, Amir Barati and Doan, Khoa D and Reddy, Chandan K},
journal={arXiv preprint arXiv:2504.10415},
year={2025}
}
@article{spiqa,
title={Spiqa: A dataset for multimodal question answering on scientific papers},
author={Pramanick, Shraman and Chellappa, Rama and Venugopalan, Subhashini},
journal={Advances in Neural Information Processing Systems},
volume={37},
pages={118807--118833},
year={2024}
}
@article{deyoung2021ms2,
title={Ms2: Multi-document summarization of medical studies},
author={DeYoung, Jay and Beltagy, Iz and van Zuylen, Madeleine and Kuehl, Bailey and Wang, Lucy Lu},
journal={arXiv preprint arXiv:2104.06486},
year={2021}
}
@inproceedings{multi-xscience,
title = "Multi-{XS}cience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles",
author = "Lu, Yao and
Dong, Yue and
Charlin, Laurent",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.648/",
doi = "10.18653/v1/2020.emnlp-main.648",
pages = "8068--8074",
abstract = "Multi-document summarization is a challenging task for which there exists little large-scale datasets. We propose Multi-XScience, a large-scale multi-document summarization dataset created from scientific articles. Multi-XScience introduces a challenging multi-document summarization task: writing the related-work section of a paper based on its abstract and the articles it references. Our work is inspired by extreme summarization, a dataset construction protocol that favours abstractive modeling approaches. Descriptive statistics and empirical results{---}using several state-of-the-art models trained on the Multi-XScience dataset{---}reveal that Multi-XScience is well suited for abstractive models."
}
@article{goldsack2022making,
title={Making science simple: Corpora for the lay summarisation of scientific literature},
author={Goldsack, Tomas and Zhang, Zhihao and Lin, Chenghua and Scarton, Carolina},
journal={arXiv preprint arXiv:2210.09932},
year={2022}
}
@article{IconShop,
author = {Wu, Ronghuan and Su, Wanchao and Ma, Kede and Liao, Jing},
title = {IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers},
year = {2023},
issue_date = {December 2023},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
volume = {42},
number = {6},
issn = {0730-0301},
url = {https://doi.org/10.1145/3618364},
doi = {10.1145/3618364},
abstract = {Scalable Vector Graphics (SVG) is a popular vector image format that offers good support for interactivity and animation. Despite its appealing characteristics, creating custom SVG content can be challenging for users due to the steep learning curve required to understand SVG grammars or get familiar with professional editing software. Recent advancements in text-to-image generation have inspired researchers to explore vector graphics synthesis using either image-based methods (i.e., text → raster image → vector graphics) combining text-to-image generation models with image vectorization, or language-based methods (i.e., text → vector graphics script) through pretrained large language models. Nevertheless, these methods suffer from limitations in terms of generation quality, diversity, and flexibility. In this paper, we introduce IconShop, a text-guided vector icon synthesis method using autoregressive transformers. The key to success of our approach is to sequentialize and tokenize SVG paths (and textual descriptions as guidance) into a uniquely decodable token sequence. With that, we are able to exploit the sequence learning power of autoregressive transformers, while enabling both unconditional and text-conditioned icon synthesis. Through standard training to predict the next token on a large-scale vector icon dataset accompanied by textural descriptions, the proposed IconShop consistently exhibits better icon synthesis capability than existing image-based and language-based methods both quantitatively (using the FID and CLIP scores) and qualitatively (through formal subjective user studies). Meanwhile, we observe a dramatic improvement in generation diversity, which is validated by the objective Uniqueness and Novelty measures. More importantly, we demonstrate the flexibility of IconShop with multiple novel icon synthesis tasks, including icon editing, icon interpolation, icon semantic combination, and icon design auto-suggestion.},
journal = {ACM Trans. Graph.},
month = dec,
articleno = {230},
numpages = {14},
keywords = {SVG, autoregressive transformers, icon synthesis, text-guided generation, vector graphics generation}
}
@article{sd_video,
title={Stable video diffusion: Scaling latent video diffusion models to large datasets},
author={Blattmann, Andreas and Dockhorn, Tim and Kulal, Sumith and Mendelevitch, Daniel and Kilian, Maciej and Lorenz, Dominik and Levi, Yam and English, Zion and Voleti, Vikram and Letts, Adam and others},
journal={arXiv preprint arXiv:2311.15127},
year={2023}
}
@article{show_1,
title={Show-1: Marrying pixel and latent diffusion models for text-to-video generation},
author={Zhang, David Junhao and Wu, Jay Zhangjie and Liu, Jia-Wei and Zhao, Rui and Ran, Lingmin and Gu, Yuchao and Gao, Difei and Shou, Mike Zheng},
journal={International Journal of Computer Vision},
volume={133},
number={4},
pages={1879--1893},
year={2025},
publisher={Springer}
}
@article{paper2agent,
title={Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents},
author={Miao, Jiacheng and Davis, Joe R and Pritchard, Jonathan K and Zou, James},
journal={arXiv preprint arXiv:2509.06917},
year={2025}
}
```
## /assets/demo/latex_proj/iclr2025_conference.bst
```bst path="/assets/demo/latex_proj/iclr2025_conference.bst"
%% File: `iclr2024.bst'
%% A copy of iclm2010.bst, which is a modification of `plainnl.bst' for use with natbib package
%%
%% Copyright 2010 Hal Daum\'e III
%% Modified by J. Fürnkranz
%% - Changed labels from (X and Y, 2000) to (X & Y, 2000)
%%
%% Copyright 1993-2007 Patrick W Daly
%% Max-Planck-Institut f\"ur Sonnensystemforschung
%% Max-Planck-Str. 2
%% D-37191 Katlenburg-Lindau
%% Germany
%% E-mail: daly@mps.mpg.de
%%
%% This program can be redistributed and/or modified under the terms
%% of the LaTeX Project Public License Distributed from CTAN
%% archives in directory macros/latex/base/lppl.txt; either
%% version 1 of the License, or any later version.
%%
% Version and source file information:
% \ProvidesFile{icml2010.mbs}[2007/11/26 1.93 (PWD)]
%
% BibTeX `plainnat' family
% version 0.99b for BibTeX versions 0.99a or later,
% for LaTeX versions 2.09 and 2e.
%
% For use with the `natbib.sty' package; emulates the corresponding
% member of the `plain' family, but with author-year citations.
%
% With version 6.0 of `natbib.sty', it may also be used for numerical
% citations, while retaining the commands \citeauthor, \citefullauthor,
% and \citeyear to print the corresponding information.
%
% For version 7.0 of `natbib.sty', the KEY field replaces missing
% authors/editors, and the date is left blank in \bibitem.
%
% Includes field EID for the sequence/citation number of electronic journals
% which is used instead of page numbers.
%
% Includes fields ISBN and ISSN.
%
% Includes field URL for Internet addresses.
%
% Includes field DOI for Digital Object Idenfifiers.
%
% Works best with the url.sty package of Donald Arseneau.
%
% Works with identical authors and year are further sorted by
% citation key, to preserve any natural sequence.
%
ENTRY
{ address
author
booktitle
chapter
doi
eid
edition
editor
howpublished
institution
isbn
issn
journal
key
month
note
number
organization
pages
publisher
school
series
title
type
url
volume
year
}
{}
{ label extra.label sort.label short.list }
INTEGERS { output.state before.all mid.sentence after.sentence after.block }
FUNCTION {init.state.consts}
{ #0 'before.all :=
#1 'mid.sentence :=
#2 'after.sentence :=
#3 'after.block :=
}
STRINGS { s t }
FUNCTION {output.nonnull}
{ 's :=
output.state mid.sentence =
{ ", " * write$ }
{ output.state after.block =
{ add.period$ write$
newline$
"\newblock " write$
}
{ output.state before.all =
'write$
{ add.period$ " " * write$ }
if$
}
if$
mid.sentence 'output.state :=
}
if$
s
}
FUNCTION {output}
{ duplicate$ empty$
'pop$
'output.nonnull
if$
}
FUNCTION {output.check}
{ 't :=
duplicate$ empty$
{ pop$ "empty " t * " in " * cite$ * warning$ }
'output.nonnull
if$
}
FUNCTION {fin.entry}
{ add.period$
write$
newline$
}
FUNCTION {new.block}
{ output.state before.all =
'skip$
{ after.block 'output.state := }
if$
}
FUNCTION {new.sentence}
{ output.state after.block =
'skip$
{ output.state before.all =
'skip$
{ after.sentence 'output.state := }
if$
}
if$
}
FUNCTION {not}
{ { #0 }
{ #1 }
if$
}
FUNCTION {and}
{ 'skip$
{ pop$ #0 }
if$
}
FUNCTION {or}
{ { pop$ #1 }
'skip$
if$
}
FUNCTION {new.block.checka}
{ empty$
'skip$
'new.block
if$
}
FUNCTION {new.block.checkb}
{ empty$
swap$ empty$
and
'skip$
'new.block
if$
}
FUNCTION {new.sentence.checka}
{ empty$
'skip$
'new.sentence
if$
}
FUNCTION {new.sentence.checkb}
{ empty$
swap$ empty$
and
'skip$
'new.sentence
if$
}
FUNCTION {field.or.null}
{ duplicate$ empty$
{ pop$ "" }
'skip$
if$
}
FUNCTION {emphasize}
{ duplicate$ empty$
{ pop$ "" }
{ "\emph{" swap$ * "}" * }
if$
}
INTEGERS { nameptr namesleft numnames }
FUNCTION {format.names}
{ 's :=
#1 'nameptr :=
s num.names$ 'numnames :=
numnames 'namesleft :=
{ namesleft #0 > }
{ s nameptr "{ff~}{vv~}{ll}{, jj}" format.name$ 't :=
nameptr #1 >
{ namesleft #1 >
{ ", " * t * }
{ numnames #2 >
{ "," * }
'skip$
if$
t "others" =
{ " et~al." * }
{ " and " * t * }
if$
}
if$
}
't
if$
nameptr #1 + 'nameptr :=
namesleft #1 - 'namesleft :=
}
while$
}
FUNCTION {format.key}
{ empty$
{ key field.or.null }
{ "" }
if$
}
FUNCTION {format.authors}
{ author empty$
{ "" }
{ author format.names }
if$
}
FUNCTION {format.editors}
{ editor empty$
{ "" }
{ editor format.names
editor num.names$ #1 >
{ " (eds.)" * }
{ " (ed.)" * }
if$
}
if$
}
FUNCTION {format.isbn}
{ isbn empty$
{ "" }
{ new.block "ISBN " isbn * }
if$
}
FUNCTION {format.issn}
{ issn empty$
{ "" }
{ new.block "ISSN " issn * }
if$
}
FUNCTION {format.url}
{ url empty$
{ "" }
{ new.block "URL \url{" url * "}" * }
if$
}
FUNCTION {format.doi}
{ doi empty$
{ "" }
{ new.block "\doi{" doi * "}" * }
if$
}
FUNCTION {format.title}
{ title empty$
{ "" }
{ title "t" change.case$ }
if$
}
FUNCTION {format.full.names}
{'s :=
#1 'nameptr :=
s num.names$ 'numnames :=
numnames 'namesleft :=
{ namesleft #0 > }
{ s nameptr
"{vv~}{ll}" format.name$ 't :=
nameptr #1 >
{
namesleft #1 >
{ ", " * t * }
{
numnames #2 >
{ "," * }
'skip$
if$
t "others" =
{ " et~al." * }
{ " and " * t * }
if$
}
if$
}
't
if$
nameptr #1 + 'nameptr :=
namesleft #1 - 'namesleft :=
}
while$
}
FUNCTION {author.editor.full}
{ author empty$
{ editor empty$
{ "" }
{ editor format.full.names }
if$
}
{ author format.full.names }
if$
}
FUNCTION {author.full}
{ author empty$
{ "" }
{ author format.full.names }
if$
}
FUNCTION {editor.full}
{ editor empty$
{ "" }
{ editor format.full.names }
if$
}
FUNCTION {make.full.names}
{ type$ "book" =
type$ "inbook" =
or
'author.editor.full
{ type$ "proceedings" =
'editor.full
'author.full
if$
}
if$
}
FUNCTION {output.bibitem}
{ newline$
"\bibitem[" write$
label write$
")" make.full.names duplicate$ short.list =
{ pop$ }
{ * }
if$
"]{" * write$
cite$ write$
"}" write$
newline$
""
before.all 'output.state :=
}
FUNCTION {n.dashify}
{ 't :=
""
{ t empty$ not }
{ t #1 #1 substring$ "-" =
{ t #1 #2 substring$ "--" = not
{ "--" *
t #2 global.max$ substring$ 't :=
}
{ { t #1 #1 substring$ "-" = }
{ "-" *
t #2 global.max$ substring$ 't :=
}
while$
}
if$
}
{ t #1 #1 substring$ *
t #2 global.max$ substring$ 't :=
}
if$
}
while$
}
FUNCTION {format.date}
{ year duplicate$ empty$
{ "empty year in " cite$ * warning$
pop$ "" }
'skip$
if$
month empty$
'skip$
{ month
" " * swap$ *
}
if$
extra.label *
}
FUNCTION {format.btitle}
{ title emphasize
}
FUNCTION {tie.or.space.connect}
{ duplicate$ text.length$ #3 <
{ "~" }
{ " " }
if$
swap$ * *
}
FUNCTION {either.or.check}
{ empty$
'pop$
{ "can't use both " swap$ * " fields in " * cite$ * warning$ }
if$
}
FUNCTION {format.bvolume}
{ volume empty$
{ "" }
{ "volume" volume tie.or.space.connect
series empty$
'skip$
{ " of " * series emphasize * }
if$
"volume and number" number either.or.check
}
if$
}
FUNCTION {format.number.series}
{ volume empty$
{ number empty$
{ series field.or.null }
{ output.state mid.sentence =
{ "number" }
{ "Number" }
if$
number tie.or.space.connect
series empty$
{ "there's a number but no series in " cite$ * warning$ }
{ " in " * series * }
if$
}
if$
}
{ "" }
if$
}
FUNCTION {format.edition}
{ edition empty$
{ "" }
{ output.state mid.sentence =
{ edition "l" change.case$ " edition" * }
{ edition "t" change.case$ " edition" * }
if$
}
if$
}
INTEGERS { multiresult }
FUNCTION {multi.page.check}
{ 't :=
#0 'multiresult :=
{ multiresult not
t empty$ not
and
}
{ t #1 #1 substring$
duplicate$ "-" =
swap$ duplicate$ "," =
swap$ "+" =
or or
{ #1 'multiresult := }
{ t #2 global.max$ substring$ 't := }
if$
}
while$
multiresult
}
FUNCTION {format.pages}
{ pages empty$
{ "" }
{ pages multi.page.check
{ "pp.\ " pages n.dashify tie.or.space.connect }
{ "pp.\ " pages tie.or.space.connect }
if$
}
if$
}
FUNCTION {format.eid}
{ eid empty$
{ "" }
{ "art." eid tie.or.space.connect }
if$
}
FUNCTION {format.vol.num.pages}
{ volume field.or.null
number empty$
'skip$
{ "\penalty0 (" number * ")" * *
volume empty$
{ "there's a number but no volume in " cite$ * warning$ }
'skip$
if$
}
if$
pages empty$
'skip$
{ duplicate$ empty$
{ pop$ format.pages }
{ ":\penalty0 " * pages n.dashify * }
if$
}
if$
}
FUNCTION {format.vol.num.eid}
{ volume field.or.null
number empty$
'skip$
{ "\penalty0 (" number * ")" * *
volume empty$
{ "there's a number but no volume in " cite$ * warning$ }
'skip$
if$
}
if$
eid empty$
'skip$
{ duplicate$ empty$
{ pop$ format.eid }
{ ":\penalty0 " * eid * }
if$
}
if$
}
FUNCTION {format.chapter.pages}
{ chapter empty$
'format.pages
{ type empty$
{ "chapter" }
{ type "l" change.case$ }
if$
chapter tie.or.space.connect
pages empty$
'skip$
{ ", " * format.pages * }
if$
}
if$
}
FUNCTION {format.in.ed.booktitle}
{ booktitle empty$
{ "" }
{ editor empty$
{ "In " booktitle emphasize * }
{ "In " format.editors * ", " * booktitle emphasize * }
if$
}
if$
}
FUNCTION {empty.misc.check}
{ author empty$ title empty$ howpublished empty$
month empty$ year empty$ note empty$
and and and and and
key empty$ not and
{ "all relevant fields are empty in " cite$ * warning$ }
'skip$
if$
}
FUNCTION {format.thesis.type}
{ type empty$
'skip$
{ pop$
type "t" change.case$
}
if$
}
FUNCTION {format.tr.number}
{ type empty$
{ "Technical Report" }
'type
if$
number empty$
{ "t" change.case$ }
{ number tie.or.space.connect }
if$
}
FUNCTION {format.article.crossref}
{ key empty$
{ journal empty$
{ "need key or journal for " cite$ * " to crossref " * crossref *
warning$
""
}
{ "In \emph{" journal * "}" * }
if$
}
{ "In " }
if$
" \citet{" * crossref * "}" *
}
FUNCTION {format.book.crossref}
{ volume empty$
{ "empty volume in " cite$ * "'s crossref of " * crossref * warning$
"In "
}
{ "Volume" volume tie.or.space.connect
" of " *
}
if$
editor empty$
editor field.or.null author field.or.null =
or
{ key empty$
{ series empty$
{ "need editor, key, or series for " cite$ * " to crossref " *
crossref * warning$
"" *
}
{ "\emph{" * series * "}" * }
if$
}
'skip$
if$
}
'skip$
if$
" \citet{" * crossref * "}" *
}
FUNCTION {format.incoll.inproc.crossref}
{ editor empty$
editor field.or.null author field.or.null =
or
{ key empty$
{ booktitle empty$
{ "need editor, key, or booktitle for " cite$ * " to crossref " *
crossref * warning$
""
}
{ "In \emph{" booktitle * "}" * }
if$
}
{ "In " }
if$
}
{ "In " }
if$
" \citet{" * crossref * "}" *
}
FUNCTION {article}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
crossref missing$
{ journal emphasize "journal" output.check
eid empty$
{ format.vol.num.pages output }
{ format.vol.num.eid output }
if$
format.date "year" output.check
}
{ format.article.crossref output.nonnull
eid empty$
{ format.pages output }
{ format.eid output }
if$
}
if$
format.issn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {book}
{ output.bibitem
author empty$
{ format.editors "author and editor" output.check
editor format.key output
}
{ format.authors output.nonnull
crossref missing$
{ "author and editor" editor either.or.check }
'skip$
if$
}
if$
new.block
format.btitle "title" output.check
crossref missing$
{ format.bvolume output
new.block
format.number.series output
new.sentence
publisher "publisher" output.check
address output
}
{ new.block
format.book.crossref output.nonnull
}
if$
format.edition output
format.date "year" output.check
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {booklet}
{ output.bibitem
format.authors output
author format.key output
new.block
format.title "title" output.check
howpublished address new.block.checkb
howpublished output
address output
format.date output
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {inbook}
{ output.bibitem
author empty$
{ format.editors "author and editor" output.check
editor format.key output
}
{ format.authors output.nonnull
crossref missing$
{ "author and editor" editor either.or.check }
'skip$
if$
}
if$
new.block
format.btitle "title" output.check
crossref missing$
{ format.bvolume output
format.chapter.pages "chapter and pages" output.check
new.block
format.number.series output
new.sentence
publisher "publisher" output.check
address output
}
{ format.chapter.pages "chapter and pages" output.check
new.block
format.book.crossref output.nonnull
}
if$
format.edition output
format.date "year" output.check
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {incollection}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
crossref missing$
{ format.in.ed.booktitle "booktitle" output.check
format.bvolume output
format.number.series output
format.chapter.pages output
new.sentence
publisher "publisher" output.check
address output
format.edition output
format.date "year" output.check
}
{ format.incoll.inproc.crossref output.nonnull
format.chapter.pages output
}
if$
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {inproceedings}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
crossref missing$
{ format.in.ed.booktitle "booktitle" output.check
format.bvolume output
format.number.series output
format.pages output
address empty$
{ organization publisher new.sentence.checkb
organization output
publisher output
format.date "year" output.check
}
{ address output.nonnull
format.date "year" output.check
new.sentence
organization output
publisher output
}
if$
}
{ format.incoll.inproc.crossref output.nonnull
format.pages output
}
if$
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {conference} { inproceedings }
FUNCTION {manual}
{ output.bibitem
format.authors output
author format.key output
new.block
format.btitle "title" output.check
organization address new.block.checkb
organization output
address output
format.edition output
format.date output
format.url output
new.block
note output
fin.entry
}
FUNCTION {mastersthesis}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
"Master's thesis" format.thesis.type output.nonnull
school "school" output.check
address output
format.date "year" output.check
format.url output
new.block
note output
fin.entry
}
FUNCTION {misc}
{ output.bibitem
format.authors output
author format.key output
title howpublished new.block.checkb
format.title output
howpublished new.block.checka
howpublished output
format.date output
format.issn output
format.url output
new.block
note output
fin.entry
empty.misc.check
}
FUNCTION {phdthesis}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.btitle "title" output.check
new.block
"PhD thesis" format.thesis.type output.nonnull
school "school" output.check
address output
format.date "year" output.check
format.url output
new.block
note output
fin.entry
}
FUNCTION {proceedings}
{ output.bibitem
format.editors output
editor format.key output
new.block
format.btitle "title" output.check
format.bvolume output
format.number.series output
address output
format.date "year" output.check
new.sentence
organization output
publisher output
format.isbn output
format.doi output
format.url output
new.block
note output
fin.entry
}
FUNCTION {techreport}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
format.tr.number output.nonnull
institution "institution" output.check
address output
format.date "year" output.check
format.url output
new.block
note output
fin.entry
}
FUNCTION {unpublished}
{ output.bibitem
format.authors "author" output.check
author format.key output
new.block
format.title "title" output.check
new.block
note "note" output.check
format.date output
format.url output
fin.entry
}
FUNCTION {default.type} { misc }
MACRO {jan} {"January"}
MACRO {feb} {"February"}
MACRO {mar} {"March"}
MACRO {apr} {"April"}
MACRO {may} {"May"}
MACRO {jun} {"June"}
MACRO {jul} {"July"}
MACRO {aug} {"August"}
MACRO {sep} {"September"}
MACRO {oct} {"October"}
MACRO {nov} {"November"}
MACRO {dec} {"December"}
MACRO {acmcs} {"ACM Computing Surveys"}
MACRO {acta} {"Acta Informatica"}
MACRO {cacm} {"Communications of the ACM"}
MACRO {ibmjrd} {"IBM Journal of Research and Development"}
MACRO {ibmsj} {"IBM Systems Journal"}
MACRO {ieeese} {"IEEE Transactions on Software Engineering"}
MACRO {ieeetc} {"IEEE Transactions on Computers"}
MACRO {ieeetcad}
{"IEEE Transactions on Computer-Aided Design of Integrated Circuits"}
MACRO {ipl} {"Information Processing Letters"}
MACRO {jacm} {"Journal of the ACM"}
MACRO {jcss} {"Journal of Computer and System Sciences"}
MACRO {scp} {"Science of Computer Programming"}
MACRO {sicomp} {"SIAM Journal on Computing"}
MACRO {tocs} {"ACM Transactions on Computer Systems"}
MACRO {tods} {"ACM Transactions on Database Systems"}
MACRO {tog} {"ACM Transactions on Graphics"}
MACRO {toms} {"ACM Transactions on Mathematical Software"}
MACRO {toois} {"ACM Transactions on Office Information Systems"}
MACRO {toplas} {"ACM Transactions on Programming Languages and Systems"}
MACRO {tcs} {"Theoretical Computer Science"}
READ
FUNCTION {sortify}
{ purify$
"l" change.case$
}
INTEGERS { len }
FUNCTION {chop.word}
{ 's :=
'len :=
s #1 len substring$ =
{ s len #1 + global.max$ substring$ }
's
if$
}
FUNCTION {format.lab.names}
{ 's :=
s #1 "{vv~}{ll}" format.name$
s num.names$ duplicate$
#2 >
{ pop$ " et~al." * }
{ #2 <
'skip$
{ s #2 "{ff }{vv }{ll}{ jj}" format.name$ "others" =
{ " et~al." * }
{ " \& " * s #2 "{vv~}{ll}" format.name$ * }
if$
}
if$
}
if$
}
FUNCTION {author.key.label}
{ author empty$
{ key empty$
{ cite$ #1 #3 substring$ }
'key
if$
}
{ author format.lab.names }
if$
}
FUNCTION {author.editor.key.label}
{ author empty$
{ editor empty$
{ key empty$
{ cite$ #1 #3 substring$ }
'key
if$
}
{ editor format.lab.names }
if$
}
{ author format.lab.names }
if$
}
FUNCTION {author.key.organization.label}
{ author empty$
{ key empty$
{ organization empty$
{ cite$ #1 #3 substring$ }
{ "The " #4 organization chop.word #3 text.prefix$ }
if$
}
'key
if$
}
{ author format.lab.names }
if$
}
FUNCTION {editor.key.organization.label}
{ editor empty$
{ key empty$
{ organization empty$
{ cite$ #1 #3 substring$ }
{ "The " #4 organization chop.word #3 text.prefix$ }
if$
}
'key
if$
}
{ editor format.lab.names }
if$
}
FUNCTION {calc.short.authors}
{ type$ "book" =
type$ "inbook" =
or
'author.editor.key.label
{ type$ "proceedings" =
'editor.key.organization.label
{ type$ "manual" =
'author.key.organization.label
'author.key.label
if$
}
if$
}
if$
'short.list :=
}
FUNCTION {calc.label}
{ calc.short.authors
short.list
"("
*
year duplicate$ empty$
short.list key field.or.null = or
{ pop$ "" }
'skip$
if$
*
'label :=
}
FUNCTION {sort.format.names}
{ 's :=
#1 'nameptr :=
""
s num.names$ 'numnames :=
numnames 'namesleft :=
{ namesleft #0 > }
{
s nameptr "{vv{ } }{ll{ }}{ ff{ }}{ jj{ }}" format.name$ 't :=
nameptr #1 >
{
" " *
namesleft #1 = t "others" = and
{ "zzzzz" * }
{ numnames #2 > nameptr #2 = and
{ "zz" * year field.or.null * " " * }
'skip$
if$
t sortify *
}
if$
}
{ t sortify * }
if$
nameptr #1 + 'nameptr :=
namesleft #1 - 'namesleft :=
}
while$
}
FUNCTION {sort.format.title}
{ 't :=
"A " #2
"An " #3
"The " #4 t chop.word
chop.word
chop.word
sortify
#1 global.max$ substring$
}
FUNCTION {author.sort}
{ author empty$
{ key empty$
{ "to sort, need author or key in " cite$ * warning$
""
}
{ key sortify }
if$
}
{ author sort.format.names }
if$
}
FUNCTION {author.editor.sort}
{ author empty$
{ editor empty$
{ key empty$
{ "to sort, need author, editor, or key in " cite$ * warning$
""
}
{ key sortify }
if$
}
{ editor sort.format.names }
if$
}
{ author sort.format.names }
if$
}
FUNCTION {author.organization.sort}
{ author empty$
{ organization empty$
{ key empty$
{ "to sort, need author, organization, or key in " cite$ * warning$
""
}
{ key sortify }
if$
}
{ "The " #4 organization chop.word sortify }
if$
}
{ author sort.format.names }
if$
}
FUNCTION {editor.organization.sort}
{ editor empty$
{ organization empty$
{ key empty$
{ "to sort, need editor, organization, or key in " cite$ * warning$
""
}
{ key sortify }
if$
}
{ "The " #4 organization chop.word sortify }
if$
}
{ editor sort.format.names }
if$
}
FUNCTION {presort}
{ calc.label
label sortify
" "
*
type$ "book" =
type$ "inbook" =
or
'author.editor.sort
{ type$ "proceedings" =
'editor.organization.sort
{ type$ "manual" =
'author.organization.sort
'author.sort
if$
}
if$
}
if$
" "
*
year field.or.null sortify
*
" "
*
cite$
*
#1 entry.max$ substring$
'sort.label :=
sort.label *
#1 entry.max$ substring$
'sort.key$ :=
}
ITERATE {presort}
SORT
STRINGS { longest.label last.label next.extra }
INTEGERS { longest.label.width last.extra.num number.label }
FUNCTION {initialize.longest.label}
{ "" 'longest.label :=
#0 int.to.chr$ 'last.label :=
"" 'next.extra :=
#0 'longest.label.width :=
#0 'last.extra.num :=
#0 'number.label :=
}
FUNCTION {forward.pass}
{ last.label label =
{ last.extra.num #1 + 'last.extra.num :=
last.extra.num int.to.chr$ 'extra.label :=
}
{ "a" chr.to.int$ 'last.extra.num :=
"" 'extra.label :=
label 'last.label :=
}
if$
number.label #1 + 'number.label :=
}
FUNCTION {reverse.pass}
{ next.extra "b" =
{ "a" 'extra.label := }
'skip$
if$
extra.label 'next.extra :=
extra.label
duplicate$ empty$
'skip$
{ "{\natexlab{" swap$ * "}}" * }
if$
'extra.label :=
label extra.label * 'label :=
}
EXECUTE {initialize.longest.label}
ITERATE {forward.pass}
REVERSE {reverse.pass}
FUNCTION {bib.sort.order}
{ sort.label 'sort.key$ :=
}
ITERATE {bib.sort.order}
SORT
FUNCTION {begin.bib}
{ preamble$ empty$
'skip$
{ preamble$ write$ newline$ }
if$
"\begin{thebibliography}{" number.label int.to.str$ * "}" *
write$ newline$
"\providecommand{\natexlab}[1]{#1}"
write$ newline$
"\providecommand{\url}[1]{\texttt{#1}}"
write$ newline$
"\expandafter\ifx\csname urlstyle\endcsname\relax"
write$ newline$
" \providecommand{\doi}[1]{doi: #1}\else"
write$ newline$
" \providecommand{\doi}{doi: \begingroup \urlstyle{rm}\Url}\fi"
write$ newline$
}
EXECUTE {begin.bib}
EXECUTE {init.state.consts}
ITERATE {call.type$}
FUNCTION {end.bib}
{ newline$
"\end{thebibliography}" write$ newline$
}
EXECUTE {end.bib}
```
## /assets/demo/latex_proj/iclr2025_conference.pdf
Binary file available at https://raw.githubusercontent.com/showlab/Paper2Video/refs/heads/main/assets/demo/latex_proj/iclr2025_conference.pdf
## /assets/demo/latex_proj/iclr2025_conference.sty
```sty path="/assets/demo/latex_proj/iclr2025_conference.sty"
%%%% ICLR Macros (LaTex)
%%%% Adapted by Hugo Larochelle from the NIPS stylefile Macros
%%%% Style File
%%%% Dec 12, 1990 Rev Aug 14, 1991; Sept, 1995; April, 1997; April, 1999; October 2014
% This file can be used with Latex2e whether running in main mode, or
% 2.09 compatibility mode.
%
% If using main mode, you need to include the commands
% \documentclass{article}
% \usepackage{iclr14submit_e,times}
%
% Change the overall width of the page. If these parameters are
% changed, they will require corresponding changes in the
% maketitle section.
%
\usepackage{eso-pic} % used by \AddToShipoutPicture
\RequirePackage{fancyhdr}
\RequirePackage{natbib}
% modification to natbib citations
\setcitestyle{authoryear,round,citesep={;},aysep={,},yysep={;}}
\renewcommand{\topfraction}{0.95} % let figure take up nearly whole page
\renewcommand{\textfraction}{0.05} % let figure take up nearly whole page
% Define iclrfinal, set to true if iclrfinalcopy is defined
\newif\ificlrfinal
\iclrfinalfalse
\def\iclrfinalcopy{\iclrfinaltrue}
\font\iclrtenhv = phvb at 8pt
% Specify the dimensions of each page
\setlength{\paperheight}{11in}
\setlength{\paperwidth}{8.5in}
\oddsidemargin .5in % Note \oddsidemargin = \evensidemargin
\evensidemargin .5in
\marginparwidth 0.07 true in
%\marginparwidth 0.75 true in
%\topmargin 0 true pt % Nominal distance from top of page to top of
%\topmargin 0.125in
\topmargin -0.625in
\addtolength{\headsep}{0.25in}
\textheight 9.0 true in % Height of text (including footnotes & figures)
\textwidth 5.5 true in % Width of text line.
\widowpenalty=10000
\clubpenalty=10000
% \thispagestyle{empty} \pagestyle{empty}
\flushbottom \sloppy
% We're never going to need a table of contents, so just flush it to
% save space --- suggested by drstrip@sandia-2
\def\addcontentsline#1#2#3{}
% Title stuff, taken from deproc.
\def\maketitle{\par
\begingroup
\def\thefootnote{\fnsymbol{footnote}}
\def\@makefnmark{\hbox to 0pt{$^{\@thefnmark}$\hss}} % for perfect author
% name centering
% The footnote-mark was overlapping the footnote-text,
% added the following to fix this problem (MK)
\long\def\@makefntext##1{\parindent 1em\noindent
\hbox to1.8em{\hss $\m@th ^{\@thefnmark}$}##1}
\@maketitle \@thanks
\endgroup
\setcounter{footnote}{0}
\let\maketitle\relax \let\@maketitle\relax
\gdef\@thanks{}\gdef\@author{}\gdef\@title{}\let\thanks\relax}
% The toptitlebar has been raised to top-justify the first page
\usepackage{fancyhdr}
\pagestyle{fancy}
\fancyhead{}
% Title (includes both anonimized and non-anonimized versions)
\def\@maketitle{\vbox{\hsize\textwidth
%\linewidth\hsize \vskip 0.1in \toptitlebar \centering
{\LARGE\sc \@title\par}
%\bottomtitlebar % \vskip 0.1in % minus
\ificlrfinal
\lhead{Published as a conference paper at ICLR 2025}
\def\And{\end{tabular}\hfil\linebreak[0]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\def\AND{\end{tabular}\hfil\linebreak[4]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\@author\end{tabular}%
\else
\lhead{Under review as a conference paper at ICLR 2025}
\def\And{\end{tabular}\hfil\linebreak[0]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\def\AND{\end{tabular}\hfil\linebreak[4]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}Anonymous authors\\Paper under double-blind review\end{tabular}%
\fi
\vskip 0.3in minus 0.1in}}
\renewenvironment{abstract}{\vskip.075in\centerline{\large\sc
Abstract}\vspace{0.5ex}\begin{quote}}{\par\end{quote}\vskip 1ex}
% sections with less space
\def\section{\@startsection {section}{1}{\z@}{-2.0ex plus
-0.5ex minus -.2ex}{1.5ex plus 0.3ex
minus0.2ex}{\large\sc\raggedright}}
\def\subsection{\@startsection{subsection}{2}{\z@}{-1.8ex plus
-0.5ex minus -.2ex}{0.8ex plus .2ex}{\normalsize\sc\raggedright}}
\def\subsubsection{\@startsection{subsubsection}{3}{\z@}{-1.5ex
plus -0.5ex minus -.2ex}{0.5ex plus
.2ex}{\normalsize\sc\raggedright}}
\def\paragraph{\@startsection{paragraph}{4}{\z@}{1.5ex plus
0.5ex minus .2ex}{-1em}{\normalsize\bf}}
\def\subparagraph{\@startsection{subparagraph}{5}{\z@}{1.5ex plus
0.5ex minus .2ex}{-1em}{\normalsize\sc}}
\def\subsubsubsection{\vskip
5pt{\noindent\normalsize\rm\raggedright}}
% Footnotes
\footnotesep 6.65pt %
\skip\footins 9pt plus 4pt minus 2pt
\def\footnoterule{\kern-3pt \hrule width 12pc \kern 2.6pt }
\setcounter{footnote}{0}
% Lists and paragraphs
\parindent 0pt
\topsep 4pt plus 1pt minus 2pt
\partopsep 1pt plus 0.5pt minus 0.5pt
\itemsep 2pt plus 1pt minus 0.5pt
\parsep 2pt plus 1pt minus 0.5pt
\parskip .5pc
%\leftmargin2em
\leftmargin3pc
\leftmargini\leftmargin \leftmarginii 2em
\leftmarginiii 1.5em \leftmarginiv 1.0em \leftmarginv .5em
%\labelsep \labelsep 5pt
\def\@listi{\leftmargin\leftmargini}
\def\@listii{\leftmargin\leftmarginii
\labelwidth\leftmarginii\advance\labelwidth-\labelsep
\topsep 2pt plus 1pt minus 0.5pt
\parsep 1pt plus 0.5pt minus 0.5pt
\itemsep \parsep}
\def\@listiii{\leftmargin\leftmarginiii
\labelwidth\leftmarginiii\advance\labelwidth-\labelsep
\topsep 1pt plus 0.5pt minus 0.5pt
\parsep \z@ \partopsep 0.5pt plus 0pt minus 0.5pt
\itemsep \topsep}
\def\@listiv{\leftmargin\leftmarginiv
\labelwidth\leftmarginiv\advance\labelwidth-\labelsep}
\def\@listv{\leftmargin\leftmarginv
\labelwidth\leftmarginv\advance\labelwidth-\labelsep}
\def\@listvi{\leftmargin\leftmarginvi
\labelwidth\leftmarginvi\advance\labelwidth-\labelsep}
\abovedisplayskip 7pt plus2pt minus5pt%
\belowdisplayskip \abovedisplayskip
\abovedisplayshortskip 0pt plus3pt%
\belowdisplayshortskip 4pt plus3pt minus3pt%
% Less leading in most fonts (due to the narrow columns)
% The choices were between 1-pt and 1.5-pt leading
%\def\@normalsize{\@setsize\normalsize{11pt}\xpt\@xpt} % got rid of @ (MK)
\def\normalsize{\@setsize\normalsize{11pt}\xpt\@xpt}
\def\small{\@setsize\small{10pt}\ixpt\@ixpt}
\def\footnotesize{\@setsize\footnotesize{10pt}\ixpt\@ixpt}
\def\scriptsize{\@setsize\scriptsize{8pt}\viipt\@viipt}
\def\tiny{\@setsize\tiny{7pt}\vipt\@vipt}
\def\large{\@setsize\large{14pt}\xiipt\@xiipt}
\def\Large{\@setsize\Large{16pt}\xivpt\@xivpt}
\def\LARGE{\@setsize\LARGE{20pt}\xviipt\@xviipt}
\def\huge{\@setsize\huge{23pt}\xxpt\@xxpt}
\def\Huge{\@setsize\Huge{28pt}\xxvpt\@xxvpt}
\def\toptitlebar{\hrule height4pt\vskip .25in\vskip-\parskip}
\def\bottomtitlebar{\vskip .29in\vskip-\parskip\hrule height1pt\vskip
.09in} %
%Reduced second vskip to compensate for adding the strut in \@author
%% % Vertical Ruler
%% % This code is, largely, from the CVPR 2010 conference style file
%% % ----- define vruler
\makeatletter
\newbox\iclrrulerbox
\newcount\iclrrulercount
\newdimen\iclrruleroffset
\newdimen\cv@lineheight
\newdimen\cv@boxheight
\newbox\cv@tmpbox
\newcount\cv@refno
\newcount\cv@tot
% NUMBER with left flushed zeros \fillzeros[<WIDTH>]<NUMBER>
\newcount\cv@tmpc@ \newcount\cv@tmpc
\def\fillzeros[#1]#2{\cv@tmpc@=#2\relax\ifnum\cv@tmpc@<0\cv@tmpc@=-\cv@tmpc@\fi
\cv@tmpc=1 %
\loop\ifnum\cv@tmpc@<10 \else \divide\cv@tmpc@ by 10 \advance\cv@tmpc by 1 \fi
\ifnum\cv@tmpc@=10\relax\cv@tmpc@=11\relax\fi \ifnum\cv@tmpc@>10 \repeat
\ifnum#2<0\advance\cv@tmpc1\relax-\fi
\loop\ifnum\cv@tmpc<#1\relax0\advance\cv@tmpc1\relax\fi \ifnum\cv@tmpc<#1 \repeat
\cv@tmpc@=#2\relax\ifnum\cv@tmpc@<0\cv@tmpc@=-\cv@tmpc@\fi \relax\the\cv@tmpc@}%
% \makevruler[<SCALE>][<INITIAL_COUNT>][<STEP>][<DIGITS>][<HEIGHT>]
\def\makevruler[#1][#2][#3][#4][#5]{\begingroup\offinterlineskip
\textheight=#5\vbadness=10000\vfuzz=120ex\overfullrule=0pt%
\global\setbox\iclrrulerbox=\vbox to \textheight{%
{\parskip=0pt\hfuzz=150em\cv@boxheight=\textheight
\cv@lineheight=#1\global\iclrrulercount=#2%
\cv@tot\cv@boxheight\divide\cv@tot\cv@lineheight\advance\cv@tot2%
\cv@refno1\vskip-\cv@lineheight\vskip1ex%
\loop\setbox\cv@tmpbox=\hbox to0cm{{\iclrtenhv\hfil\fillzeros[#4]\iclrrulercount}}%
\ht\cv@tmpbox\cv@lineheight\dp\cv@tmpbox0pt\box\cv@tmpbox\break
\advance\cv@refno1\global\advance\iclrrulercount#3\relax
\ifnum\cv@refno<\cv@tot\repeat}}\endgroup}%
\makeatother
% ----- end of vruler
% \makevruler[<SCALE>][<INITIAL_COUNT>][<STEP>][<DIGITS>][<HEIGHT>]
\def\iclrruler#1{\makevruler[12pt][#1][1][3][0.993\textheight]\usebox{\iclrrulerbox}}
\AddToShipoutPicture{%
\ificlrfinal\else
\iclrruleroffset=\textheight
\advance\iclrruleroffset by -3.7pt
\color[rgb]{.7,.7,.7}
\AtTextUpperLeft{%
\put(\LenToUnit{-35pt},\LenToUnit{-\iclrruleroffset}){%left ruler
\iclrruler{\iclrrulercount}}
}
\fi
}
% %% To add a vertical bar on the side
% \AddToShipoutPicture{
% \AtTextLowerLeft{
% \hspace*{-1.8cm}
% \colorbox[rgb]{0.7,0.7,0.7}{\small \parbox[b][\textheight]{0.1cm}{}}}
% }
```
## /assets/demo/latex_proj/iclr2025_conference.tex
```tex path="/assets/demo/latex_proj/iclr2025_conference.tex"
\PassOptionsToPackage{numbers}{natbib}
\documentclass{article} % For LaTeX2e
\usepackage{iclr2026_paper,times}
\usepackage[utf8]{inputenc} % allow utf-8 input
\usepackage[T1]{fontenc} % use 8-bit T1 fonts
% \usepackage{hyperref} % hyperlinks
\usepackage{url} % simple URL typesetting
\usepackage{booktabs} % professional-quality tables
\usepackage{amsfonts} % blackboard math symbols
\usepackage{nicefrac} % compact symbols for 1/2, etc.
\usepackage{microtype} % microtypography
\usepackage{xcolor} % colors
\usepackage{marvosym}
\usepackage{fontawesome}
\usepackage{pifont}
\usepackage{multirow}
\usepackage{graphicx}
\usepackage{amsmath}
\usepackage{amssymb}
\usepackage{algorithm,algpseudocode}
\usepackage{wrapfig}
\usepackage{booktabs}
\usepackage{xcolor}
% \usepackage{hyperref}
\usepackage{titlesec} % 提供 \titleformat
\usepackage{titletoc} % 提供 \startcontents / \printcontents / \titlecontents
% \usepackage{natbib}
% \usepackage[numbers,sort&compress]{natbib}
\usepackage[most]{tcolorbox}
\usepackage{xcolor}
\usepackage{enumitem}
\usepackage{tikz} % 仅用于标题左侧的小圆点
% \usepackage[colorlinks=true]{hyperref}
\setcitestyle{square,numbers,comma,sort&compress}
\usepackage{enumitem}
\usepackage{colortbl} % 提供 \rowcolor
\usepackage[table]{xcolor} % 定义灰色等颜色
\usepackage{tabularx} % 导言区
\definecolor{myviolet}{HTML}{9B8AFB}
\definecolor{grayblue}{RGB}{170, 180, 230}
\definecolor{lightblue}{RGB}{150, 200, 255}
% \definecolor{citecolor}{HTML}{grayblue}
\definecolor{citecolor}{HTML}{0071bc}
\usepackage[pagebackref=false,breaklinks=true,letterpaper=true,colorlinks,citecolor=citecolor,bookmarks=false]{hyperref}
% \PassOptionsToPackage{numbers,sort&compress}{natbib}
% \usepackage[preprint]{neurips_2025}
% \usepackage[dblblindworkshop]{neurips_2025}
\usepackage{titlesec}
\titlespacing*{\subsection}{0pt}{0.1\baselineskip}{0.25\baselineskip}
\titlespacing*{\section}{0pt}{0.1\baselineskip}{0.1\baselineskip}
\titlespacing*{\subsection}{0pt}{0.1\baselineskip}{0.15\baselineskip}
\setlength{\textfloatsep}{3pt} % 浮动体与上下文之间的距离（默认约 20pt）
\setlength{\floatsep}{3pt} % 两个浮动体之间的距离
\setlength{\intextsep}{4pt} % 内嵌浮动体与上下文之间
\titlespacing{\section}{0pt}{*0.1}{*0.1}
\titlespacing{\subsection}{0pt}{*0.1}{*0.1}
\titlespacing{\subsubsection}{0pt}{*0.1}{*0.1}
% 全局：所有 figure 的图-题注间距
\usepackage{caption}
\captionsetup[figure]{skip=2pt}
\captionsetup[table]{skip=1pt}
\newcommand{\cmark}{\ding{51}} % ✓
\newcommand{\xmark}{\ding{55}} % ✗
\newcommand{\ie}{\textit{i.e.,}} % ✓
\newcommand{\eg}{\textit{e.g.,}} % ✓
\newcommand{\kevin}[1]{\textcolor{blue}{(Kevin: #1)}}
\newcommand{\tablesize}{\fontsize{8pt}{8pt}\selectfont}
\newcommand{\our}{Paper2Video}
\newcommand{\bench}{Paper2Video}
% \newcommand{\agent}{PaperShow}
\newcommand{\agent}{PaperTalker}
% Note. For the workshop paper template, both \title{} and \workshoptitle{} are required, with the former indicating the paper title shown in the title and the latter indicating the workshop title displayed in the footnote.
\title{\includegraphics[width=0.7cm, height=0.7cm]{figure/logo_.png} Paper2Video:
Automatic Video Generation from Scientific Papers}
% The \author macro works with any number of authors. There are two commands
% used to separate the names and addresses of multiple authors: \And and \AND.
%
% Using \And between authors leaves it to LaTeX to determine where to break the
% lines. Using \AND forces a line break at that point. So, if LaTeX puts 3 of 4
% authors names on the first line, and the last on the second line, try using
% \AND instead of \And before the third author name.
\author{
Zeyu Zhu\textsuperscript{*},
Kevin Qinghong Lin\textsuperscript{*},
Mike Zheng Shou\textsuperscript{\Letter}\\
\\
Show Lab, National University of Singapore \\
}
\iclrfinalcopy
\begin{document}
\maketitle
\let\thefootnote\relax
\footnotetext{$^*$ Equal contribution.}
\let\thefootnote\relax
\footnotetext{$^{\textrm{\Letter}}$ Corresponding author.}
\vspace{-2\baselineskip}
\begin{abstract}
\vspace{-1\baselineskip}
Academic presentation videos have become an essential medium for research communication, yet producing them remains highly labor-intensive, often requiring hours of slide design, recording, and editing for a short 2 to 10 minutes video.
Unlike natural video, presentation video generation involves distinctive challenges: long-context inputs from research papers, dense multi-modal information (text, figures, tables), and the need to coordinate multiple aligned channels such as slides, subtitles, speech, and human talker.
To address these challenges, we introduce \textbf{\bench}, the first benchmark of 101 research papers paired with author-created presentation videos, slides, and speaker metadata. We further design four tailored evaluation metrics—Meta Similarity, PresentArena, \textit{PresentQuiz}, and \textit{IP Memory}—to measure how videos convey the paper's information to the audience. Building on this foundation, we propose \textbf{\agent}, the first multi-agent framework for academic presentation video generation. It integrates slide generation with effective layout refinement by a novel effective \textit{Tree Search Visual Choice}, cursor grounding, subtitling, speech synthesis, and talking-head rendering, while parallelizing slide-wise generation for efficiency. Experiments on \bench~demonstrate that the presentation videos produced by our approach are more faithful and informative than existing baselines, establishing a practical step toward automated and ready-to-use academic video generation.
% Our datasets, agent, and codes will be \textit{fully open-sourced} to power the community.
\end{abstract}
\input{section/introduction.tex}
\input{section/related_work.tex}
\input{section/benchmark.tex}
\input{section/method.tex}
\input{section/experiment}
\input{section/conclusion}
\newpage
\bibliographystyle{plainnat}
\bibliography{iclr2025_conference}
\newpage
\input{section/appendix}
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
% \appendix
% \section{Technical Appendices and Supplementary Material}
% Technical appendices with additional results, figures, graphs and proofs may be submitted with the paper submission before the full submission deadline (see above), or as a separate PDF in the ZIP file below before the supplementary material deadline. There is no page limit for the technical appendices.
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
\end{document}
```
## /assets/demo/latex_proj/iclr2026_paper.sty
```sty path="/assets/demo/latex_proj/iclr2026_paper.sty"
%%%% ICLR Macros (LaTex)
%%%% Adapted by Hugo Larochelle from the NIPS stylefile Macros
%%%% Style File
%%%% Dec 12, 1990 Rev Aug 14, 1991; Sept, 1995; April, 1997; April, 1999; October 2014
% This file can be used with Latex2e whether running in main mode, or
% 2.09 compatibility mode.
%
% If using main mode, you need to include the commands
% \documentclass{article}
% \usepackage{iclr14submit_e,times}
%
% Change the overall width of the page. If these parameters are
% changed, they will require corresponding changes in the
% maketitle section.
%
\usepackage{eso-pic} % used by \AddToShipoutPicture
\RequirePackage{fancyhdr}
\RequirePackage{natbib}
% modification to natbib citations
\setcitestyle{authoryear,round,citesep={;},aysep={,},yysep={;}}
\renewcommand{\topfraction}{0.95} % let figure take up nearly whole page
\renewcommand{\textfraction}{0.05} % let figure take up nearly whole page
% Define iclrfinal, set to true if iclrfinalcopy is defined
\newif\ificlrfinal
\iclrfinalfalse
\def\iclrfinalcopy{\iclrfinaltrue}
\font\iclrtenhv = phvb at 8pt
% Specify the dimensions of each page
\setlength{\paperheight}{11in}
\setlength{\paperwidth}{8.5in}
\oddsidemargin .5in % Note \oddsidemargin = \evensidemargin
\evensidemargin .5in
\marginparwidth 0.07 true in
%\marginparwidth 0.75 true in
%\topmargin 0 true pt % Nominal distance from top of page to top of
%\topmargin 0.125in
\topmargin -0.625in
\addtolength{\headsep}{0.25in}
\textheight 9.0 true in % Height of text (including footnotes & figures)
\textwidth 5.5 true in % Width of text line.
\widowpenalty=10000
\clubpenalty=10000
% \thispagestyle{empty} \pagestyle{empty}
\flushbottom \sloppy
% We're never going to need a table of contents, so just flush it to
% save space --- suggested by drstrip@sandia-2
\def\addcontentsline#1#2#3{}
% Title stuff, taken from deproc.
\def\maketitle{\par
\begingroup
\def\thefootnote{\fnsymbol{footnote}}
\def\@makefnmark{\hbox to 0pt{$^{\@thefnmark}$\hss}} % for perfect author
% name centering
% The footnote-mark was overlapping the footnote-text,
% added the following to fix this problem (MK)
\long\def\@makefntext##1{\parindent 1em\noindent
\hbox to1.8em{\hss $\m@th ^{\@thefnmark}$}##1}
\@maketitle \@thanks
\endgroup
\setcounter{footnote}{0}
\let\maketitle\relax \let\@maketitle\relax
\gdef\@thanks{}\gdef\@author{}\gdef\@title{}\let\thanks\relax}
% The toptitlebar has been raised to top-justify the first page
\usepackage{fancyhdr}
\pagestyle{fancy}
\fancyhead{}
% Title (includes both anonimized and non-anonimized versions)
\def\@maketitle{\vbox{\hsize\textwidth
%\linewidth\hsize \vskip 0.1in \toptitlebar \centering
{\LARGE\sc \@title\par}
%\bottomtitlebar % \vskip 0.1in % minus
\ificlrfinal
\lhead{preprint}
\def\And{\end{tabular}\hfil\linebreak[0]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\def\AND{\end{tabular}\hfil\linebreak[4]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\@author\end{tabular}%
\else
\lhead{preprint}
\def\And{\end{tabular}\hfil\linebreak[0]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\def\AND{\end{tabular}\hfil\linebreak[4]\hfil
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}\ignorespaces}%
\begin{tabular}[t]{l}\bf\rule{\z@}{24pt}Anonymous authors\\Paper under double-blind review\end{tabular}%
\fi
\vskip 0.3in minus 0.1in}}
\renewenvironment{abstract}{\vskip.075in\centerline{\large\sc
Abstract}\vspace{0.5ex}\begin{quote}}{\par\end{quote}\vskip 1ex}
% sections with less space
\def\section{\@startsection {section}{1}{\z@}{-2.0ex plus
-0.5ex minus -.2ex}{1.5ex plus 0.3ex
minus0.2ex}{\large\sc\raggedright}}
\def\subsection{\@startsection{subsection}{2}{\z@}{-1.8ex plus
-0.5ex minus -.2ex}{0.8ex plus .2ex}{\normalsize\sc\raggedright}}
\def\subsubsection{\@startsection{subsubsection}{3}{\z@}{-1.5ex
plus -0.5ex minus -.2ex}{0.5ex plus
.2ex}{\normalsize\sc\raggedright}}
\def\paragraph{\@startsection{paragraph}{4}{\z@}{1.5ex plus
0.5ex minus .2ex}{-1em}{\normalsize\bf}}
\def\subparagraph{\@startsection{subparagraph}{5}{\z@}{1.5ex plus
0.5ex minus .2ex}{-1em}{\normalsize\sc}}
\def\subsubsubsection{\vskip
5pt{\noindent\normalsize\rm\raggedright}}
% Footnotes
\footnotesep 6.65pt %
\skip\footins 9pt plus 4pt minus 2pt
\def\footnoterule{\kern-3pt \hrule width 12pc \kern 2.6pt }
\setcounter{footnote}{0}
% Lists and paragraphs
\parindent 0pt
\topsep 4pt plus 1pt minus 2pt
\partopsep 1pt plus 0.5pt minus 0.5pt
\itemsep 2pt plus 1pt minus 0.5pt
\parsep 2pt plus 1pt minus 0.5pt
\parskip .5pc
%\leftmargin2em
\leftmargin3pc
\leftmargini\leftmargin \leftmarginii 2em
\leftmarginiii 1.5em \leftmarginiv 1.0em \leftmarginv .5em
%\labelsep \labelsep 5pt
\def\@listi{\leftmargin\leftmargini}
\def\@listii{\leftmargin\leftmarginii
\labelwidth\leftmarginii\advance\labelwidth-\labelsep
\topsep 2pt plus 1pt minus 0.5pt
\parsep 1pt plus 0.5pt minus 0.5pt
\itemsep \parsep}
\def\@listiii{\leftmargin\leftmarginiii
\labelwidth\leftmarginiii\advance\labelwidth-\labelsep
\topsep 1pt plus 0.5pt minus 0.5pt
\parsep \z@ \partopsep 0.5pt plus 0pt minus 0.5pt
\itemsep \topsep}
\def\@listiv{\leftmargin\leftmarginiv
\labelwidth\leftmarginiv\advance\labelwidth-\labelsep}
\def\@listv{\leftmargin\leftmarginv
\labelwidth\leftmarginv\advance\labelwidth-\labelsep}
\def\@listvi{\leftmargin\leftmarginvi
\labelwidth\leftmarginvi\advance\labelwidth-\labelsep}
\abovedisplayskip 7pt plus2pt minus5pt%
\belowdisplayskip \abovedisplayskip
\abovedisplayshortskip 0pt plus3pt%
\belowdisplayshortskip 4pt plus3pt minus3pt%
% Less leading in most fonts (due to the narrow columns)
% The choices were between 1-pt and 1.5-pt leading
%\def\@normalsize{\@setsize\normalsize{11pt}\xpt\@xpt} % got rid of @ (MK)
\def\normalsize{\@setsize\normalsize{11pt}\xpt\@xpt}
\def\small{\@setsize\small{10pt}\ixpt\@ixpt}
\def\footnotesize{\@setsize\footnotesize{10pt}\ixpt\@ixpt}
\def\scriptsize{\@setsize\scriptsize{8pt}\viipt\@viipt}
\def\tiny{\@setsize\tiny{7pt}\vipt\@vipt}
\def\large{\@setsize\large{14pt}\xiipt\@xiipt}
\def\Large{\@setsize\Large{16pt}\xivpt\@xivpt}
\def\LARGE{\@setsize\LARGE{20pt}\xviipt\@xviipt}
\def\huge{\@setsize\huge{23pt}\xxpt\@xxpt}
\def\Huge{\@setsize\Huge{28pt}\xxvpt\@xxvpt}
\def\toptitlebar{\hrule height4pt\vskip .25in\vskip-\parskip}
\def\bottomtitlebar{\vskip .29in\vskip-\parskip\hrule height1pt\vskip
.09in} %
%Reduced second vskip to compensate for adding the strut in \@author
%% % Vertical Ruler
%% % This code is, largely, from the CVPR 2010 conference style file
%% % ----- define vruler
\makeatletter
\newbox\iclrrulerbox
\newcount\iclrrulercount
\newdimen\iclrruleroffset
\newdimen\cv@lineheight
\newdimen\cv@boxheight
\newbox\cv@tmpbox
\newcount\cv@refno
\newcount\cv@tot
% NUMBER with left flushed zeros \fillzeros[<WIDTH>]<NUMBER>
\newcount\cv@tmpc@ \newcount\cv@tmpc
\def\fillzeros[#1]#2{\cv@tmpc@=#2\relax\ifnum\cv@tmpc@<0\cv@tmpc@=-\cv@tmpc@\fi
\cv@tmpc=1 %
\loop\ifnum\cv@tmpc@<10 \else \divide\cv@tmpc@ by 10 \advance\cv@tmpc by 1 \fi
\ifnum\cv@tmpc@=10\relax\cv@tmpc@=11\relax\fi \ifnum\cv@tmpc@>10 \repeat
\ifnum#2<0\advance\cv@tmpc1\relax-\fi
\loop\ifnum\cv@tmpc<#1\relax0\advance\cv@tmpc1\relax\fi \ifnum\cv@tmpc<#1 \repeat
\cv@tmpc@=#2\relax\ifnum\cv@tmpc@<0\cv@tmpc@=-\cv@tmpc@\fi \relax\the\cv@tmpc@}%
% \makevruler[<SCALE>][<INITIAL_COUNT>][<STEP>][<DIGITS>][<HEIGHT>]
\def\makevruler[#1][#2][#3][#4][#5]{\begingroup\offinterlineskip
\textheight=#5\vbadness=10000\vfuzz=120ex\overfullrule=0pt%
\global\setbox\iclrrulerbox=\vbox to \textheight{%
{\parskip=0pt\hfuzz=150em\cv@boxheight=\textheight
\cv@lineheight=#1\global\iclrrulercount=#2%
\cv@tot\cv@boxheight\divide\cv@tot\cv@lineheight\advance\cv@tot2%
\cv@refno1\vskip-\cv@lineheight\vskip1ex%
\loop\setbox\cv@tmpbox=\hbox to0cm{{\iclrtenhv\hfil\fillzeros[#4]\iclrrulercount}}%
\ht\cv@tmpbox\cv@lineheight\dp\cv@tmpbox0pt\box\cv@tmpbox\break
\advance\cv@refno1\global\advance\iclrrulercount#3\relax
\ifnum\cv@refno<\cv@tot\repeat}}\endgroup}%
\makeatother
% ----- end of vruler
% \makevruler[<SCALE>][<INITIAL_COUNT>][<STEP>][<DIGITS>][<HEIGHT>]
\def\iclrruler#1{\makevruler[12pt][#1][1][3][0.993\textheight]\usebox{\iclrrulerbox}}
\AddToShipoutPicture{%
\ificlrfinal\else
\iclrruleroffset=\textheight
\advance\iclrruleroffset by -3.7pt
\color[rgb]{.7,.7,.7}
\AtTextUpperLeft{%
\put(\LenToUnit{-35pt},\LenToUnit{-\iclrruleroffset}){%left ruler
\iclrruler{\iclrrulercount}}
}
\fi
}
% %% To add a vertical bar on the side
% \AddToShipoutPicture{
% \AtTextLowerLeft{
% \hspace*{-1.8cm}
% \colorbox[rgb]{0.7,0.7,0.7}{\small \parbox[b][\textheight]{0.1cm}{}}}
% }
```
## /assets/demo/latex_proj/math_commands.tex
```tex path="/assets/demo/latex_proj/math_commands.tex"
%%%%% NEW MATH DEFINITIONS %%%%%
\usepackage{amsmath,amsfonts,bm}
% Mark sections of captions for referring to divisions of figures
\newcommand{\figleft}{{\em (Left)}}
\newcommand{\figcenter}{{\em (Center)}}
\newcommand{\figright}{{\em (Right)}}
\newcommand{\figtop}{{\em (Top)}}
\newcommand{\figbottom}{{\em (Bottom)}}
\newcommand{\captiona}{{\em (a)}}
\newcommand{\captionb}{{\em (b)}}
\newcommand{\captionc}{{\em (c)}}
\newcommand{\captiond}{{\em (d)}}
% Highlight a newly defined term
\newcommand{\newterm}[1]{{\bf #1}}
% Figure reference, lower-case.
\def\figref#1{figure~\ref{#1}}
% Figure reference, capital. For start of sentence
\def\Figref#1{Figure~\ref{#1}}
\def\twofigref#1#2{figures \ref{#1} and \ref{#2}}
\def\quadfigref#1#2#3#4{figures \ref{#1}, \ref{#2}, \ref{#3} and \ref{#4}}
% Section reference, lower-case.
\def\secref#1{section~\ref{#1}}
% Section reference, capital.
\def\Secref#1{Section~\ref{#1}}
% Reference to two sections.
\def\twosecrefs#1#2{sections \ref{#1} and \ref{#2}}
% Reference to three sections.
\def\secrefs#1#2#3{sections \ref{#1}, \ref{#2} and \ref{#3}}
% Reference to an equation, lower-case.
\def\eqref#1{equation~\ref{#1}}
% Reference to an equation, upper case
\def\Eqref#1{Equation~\ref{#1}}
% A raw reference to an equation---avoid using if possible
\def\plaineqref#1{\ref{#1}}
% Reference to a chapter, lower-case.
\def\chapref#1{chapter~\ref{#1}}
% Reference to an equation, upper case.
\def\Chapref#1{Chapter~\ref{#1}}
% Reference to a range of chapters
\def\rangechapref#1#2{chapters\ref{#1}--\ref{#2}}
% Reference to an algorithm, lower-case.
\def\algref#1{algorithm~\ref{#1}}
% Reference to an algorithm, upper case.
\def\Algref#1{Algorithm~\ref{#1}}
\def\twoalgref#1#2{algorithms \ref{#1} and \ref{#2}}
\def\Twoalgref#1#2{Algorithms \ref{#1} and \ref{#2}}
% Reference to a part, lower case
\def\partref#1{part~\ref{#1}}
% Reference to a part, upper case
\def\Partref#1{Part~\ref{#1}}
\def\twopartref#1#2{parts \ref{#1} and \ref{#2}}
\def\ceil#1{\lceil #1 \rceil}
\def\floor#1{\lfloor #1 \rfloor}
\def\1{\bm{1}}
\newcommand{\train}{\mathcal{D}}
\newcommand{\valid}{\mathcal{D_{\mathrm{valid}}}}
\newcommand{\test}{\mathcal{D_{\mathrm{test}}}}
\def\eps{{\epsilon}}
% Random variables
\def\reta{{\textnormal{$\eta$}}}
\def\ra{{\textnormal{a}}}
\def\rb{{\textnormal{b}}}
\def\rc{{\textnormal{c}}}
\def\rd{{\textnormal{d}}}
\def\re{{\textnormal{e}}}
\def\rf{{\textnormal{f}}}
\def\rg{{\textnormal{g}}}
\def\rh{{\textnormal{h}}}
\def\ri{{\textnormal{i}}}
\def\rj{{\textnormal{j}}}
\def\rk{{\textnormal{k}}}
\def\rl{{\textnormal{l}}}
% rm is already a command, just don't name any random variables m
\def\rn{{\textnormal{n}}}
\def\ro{{\textnormal{o}}}
\def\rp{{\textnormal{p}}}
\def\rq{{\textnormal{q}}}
\def\rr{{\textnormal{r}}}
\def\rs{{\textnormal{s}}}
\def\rt{{\textnormal{t}}}
\def\ru{{\textnormal{u}}}
\def\rv{{\textnormal{v}}}
\def\rw{{\textnormal{w}}}
\def\rx{{\textnormal{x}}}
\def\ry{{\textnormal{y}}}
\def\rz{{\textnormal{z}}}
% Random vectors
\def\rvepsilon{{\mathbf{\epsilon}}}
\def\rvtheta{{\mathbf{\theta}}}
\def\rva{{\mathbf{a}}}
\def\rvb{{\mathbf{b}}}
\def\rvc{{\mathbf{c}}}
\def\rvd{{\mathbf{d}}}
\def\rve{{\mathbf{e}}}
\def\rvf{{\mathbf{f}}}
\def\rvg{{\mathbf{g}}}
\def\rvh{{\mathbf{h}}}
\def\rvu{{\mathbf{i}}}
\def\rvj{{\mathbf{j}}}
\def\rvk{{\mathbf{k}}}
\def\rvl{{\mathbf{l}}}
\def\rvm{{\mathbf{m}}}
\def\rvn{{\mathbf{n}}}
\def\rvo{{\mathbf{o}}}
\def\rvp{{\mathbf{p}}}
\def\rvq{{\mathbf{q}}}
\def\rvr{{\mathbf{r}}}
\def\rvs{{\mathbf{s}}}
\def\rvt{{\mathbf{t}}}
\def\rvu{{\mathbf{u}}}
\def\rvv{{\mathbf{v}}}
\def\rvw{{\mathbf{w}}}
\def\rvx{{\mathbf{x}}}
\def\rvy{{\mathbf{y}}}
\def\rvz{{\mathbf{z}}}
% Elements of random vectors
\def\erva{{\textnormal{a}}}
\def\ervb{{\textnormal{b}}}
\def\ervc{{\textnormal{c}}}
\def\ervd{{\textnormal{d}}}
\def\erve{{\textnormal{e}}}
\def\ervf{{\textnormal{f}}}
\def\ervg{{\textnormal{g}}}
\def\ervh{{\textnormal{h}}}
\def\ervi{{\textnormal{i}}}
\def\ervj{{\textnormal{j}}}
\def\ervk{{\textnormal{k}}}
\def\ervl{{\textnormal{l}}}
\def\ervm{{\textnormal{m}}}
\def\ervn{{\textnormal{n}}}
\def\ervo{{\textnormal{o}}}
\def\ervp{{\textnormal{p}}}
\def\ervq{{\textnormal{q}}}
\def\ervr{{\textnormal{r}}}
\def\ervs{{\textnormal{s}}}
\def\ervt{{\textnormal{t}}}
\def\ervu{{\textnormal{u}}}
\def\ervv{{\textnormal{v}}}
\def\ervw{{\textnormal{w}}}
\def\ervx{{\textnormal{x}}}
\def\ervy{{\textnormal{y}}}
\def\ervz{{\textnormal{z}}}
% Random matrices
\def\rmA{{\mathbf{A}}}
\def\rmB{{\mathbf{B}}}
\def\rmC{{\mathbf{C}}}
\def\rmD{{\mathbf{D}}}
\def\rmE{{\mathbf{E}}}
\def\rmF{{\mathbf{F}}}
\def\rmG{{\mathbf{G}}}
\def\rmH{{\mathbf{H}}}
\def\rmI{{\mathbf{I}}}
\def\rmJ{{\mathbf{J}}}
\def\rmK{{\mathbf{K}}}
\def\rmL{{\mathbf{L}}}
\def\rmM{{\mathbf{M}}}
\def\rmN{{\mathbf{N}}}
\def\rmO{{\mathbf{O}}}
\def\rmP{{\mathbf{P}}}
\def\rmQ{{\mathbf{Q}}}
\def\rmR{{\mathbf{R}}}
\def\rmS{{\mathbf{S}}}
\def\rmT{{\mathbf{T}}}
\def\rmU{{\mathbf{U}}}
\def\rmV{{\mathbf{V}}}
\def\rmW{{\mathbf{W}}}
\def\rmX{{\mathbf{X}}}
\def\rmY{{\mathbf{Y}}}
\def\rmZ{{\mathbf{Z}}}
% Elements of random matrices
\def\ermA{{\textnormal{A}}}
\def\ermB{{\textnormal{B}}}
\def\ermC{{\textnormal{C}}}
\def\ermD{{\textnormal{D}}}
\def\ermE{{\textnormal{E}}}
\def\ermF{{\textnormal{F}}}
\def\ermG{{\textnormal{G}}}
\def\ermH{{\textnormal{H}}}
\def\ermI{{\textnormal{I}}}
\def\ermJ{{\textnormal{J}}}
\def\ermK{{\textnormal{K}}}
\def\ermL{{\textnormal{L}}}
\def\ermM{{\textnormal{M}}}
\def\ermN{{\textnormal{N}}}
\def\ermO{{\textnormal{O}}}
\def\ermP{{\textnormal{P}}}
\def\ermQ{{\textnormal{Q}}}
\def\ermR{{\textnormal{R}}}
\def\ermS{{\textnormal{S}}}
\def\ermT{{\textnormal{T}}}
\def\ermU{{\textnormal{U}}}
\def\ermV{{\textnormal{V}}}
\def\ermW{{\textnormal{W}}}
\def\ermX{{\textnormal{X}}}
\def\ermY{{\textnormal{Y}}}
\def\ermZ{{\textnormal{Z}}}
% Vectors
\def\vzero{{\bm{0}}}
\def\vone{{\bm{1}}}
\def\vmu{{\bm{\mu}}}
\def\vtheta{{\bm{\theta}}}
\def\va{{\bm{a}}}
\def\vb{{\bm{b}}}
\def\vc{{\bm{c}}}
\def\vd{{\bm{d}}}
\def\ve{{\bm{e}}}
\def\vf{{\bm{f}}}
\def\vg{{\bm{g}}}
\def\vh{{\bm{h}}}
\def\vi{{\bm{i}}}
\def\vj{{\bm{j}}}
\def\vk{{\bm{k}}}
\def\vl{{\bm{l}}}
\def\vm{{\bm{m}}}
\def\vn{{\bm{n}}}
\def\vo{{\bm{o}}}
\def\vp{{\bm{p}}}
\def\vq{{\bm{q}}}
\def\vr{{\bm{r}}}
\def\vs{{\bm{s}}}
\def\vt{{\bm{t}}}
\def\vu{{\bm{u}}}
\def\vv{{\bm{v}}}
\def\vw{{\bm{w}}}
\def\vx{{\bm{x}}}
\def\vy{{\bm{y}}}
\def\vz{{\bm{z}}}
% Elements of vectors
\def\evalpha{{\alpha}}
\def\evbeta{{\beta}}
\def\evepsilon{{\epsilon}}
\def\evlambda{{\lambda}}
\def\evomega{{\omega}}
\def\evmu{{\mu}}
\def\evpsi{{\psi}}
\def\evsigma{{\sigma}}
\def\evtheta{{\theta}}
\def\eva{{a}}
\def\evb{{b}}
\def\evc{{c}}
\def\evd{{d}}
\def\eve{{e}}
\def\evf{{f}}
\def\evg{{g}}
\def\evh{{h}}
\def\evi{{i}}
\def\evj{{j}}
\def\evk{{k}}
\def\evl{{l}}
\def\evm{{m}}
\def\evn{{n}}
\def\evo{{o}}
\def\evp{{p}}
\def\evq{{q}}
\def\evr{{r}}
\def\evs{{s}}
\def\evt{{t}}
\def\evu{{u}}
\def\evv{{v}}
\def\evw{{w}}
\def\evx{{x}}
\def\evy{{y}}
\def\evz{{z}}
% Matrix
\def\mA{{\bm{A}}}
\def\mB{{\bm{B}}}
\def\mC{{\bm{C}}}
\def\mD{{\bm{D}}}
\def\mE{{\bm{E}}}
\def\mF{{\bm{F}}}
\def\mG{{\bm{G}}}
\def\mH{{\bm{H}}}
\def\mI{{\bm{I}}}
\def\mJ{{\bm{J}}}
\def\mK{{\bm{K}}}
\def\mL{{\bm{L}}}
\def\mM{{\bm{M}}}
\def\mN{{\bm{N}}}
\def\mO{{\bm{O}}}
\def\mP{{\bm{P}}}
\def\mQ{{\bm{Q}}}
\def\mR{{\bm{R}}}
\def\mS{{\bm{S}}}
\def\mT{{\bm{T}}}
\def\mU{{\bm{U}}}
\def\mV{{\bm{V}}}
\def\mW{{\bm{W}}}
\def\mX{{\bm{X}}}
\def\mY{{\bm{Y}}}
\def\mZ{{\bm{Z}}}
\def\mBeta{{\bm{\beta}}}
\def\mPhi{{\bm{\Phi}}}
\def\mLambda{{\bm{\Lambda}}}
\def\mSigma{{\bm{\Sigma}}}
% Tensor
\DeclareMathAlphabet{\mathsfit}{\encodingdefault}{\sfdefault}{m}{sl}
\SetMathAlphabet{\mathsfit}{bold}{\encodingdefault}{\sfdefault}{bx}{n}
\newcommand{\tens}[1]{\bm{\mathsfit{#1}}}
\def\tA{{\tens{A}}}
\def\tB{{\tens{B}}}
\def\tC{{\tens{C}}}
\def\tD{{\tens{D}}}
\def\tE{{\tens{E}}}
\def\tF{{\tens{F}}}
\def\tG{{\tens{G}}}
\def\tH{{\tens{H}}}
\def\tI{{\tens{I}}}
\def\tJ{{\tens{J}}}
\def\tK{{\tens{K}}}
\def\tL{{\tens{L}}}
\def\tM{{\tens{M}}}
\def\tN{{\tens{N}}}
\def\tO{{\tens{O}}}
\def\tP{{\tens{P}}}
\def\tQ{{\tens{Q}}}
\def\tR{{\tens{R}}}
\def\tS{{\tens{S}}}
\def\tT{{\tens{T}}}
\def\tU{{\tens{U}}}
\def\tV{{\tens{V}}}
\def\tW{{\tens{W}}}
\def\tX{{\tens{X}}}
\def\tY{{\tens{Y}}}
\def\tZ{{\tens{Z}}}
% Graph
\def\gA{{\mathcal{A}}}
\def\gB{{\mathcal{B}}}
\def\gC{{\mathcal{C}}}
\def\gD{{\mathcal{D}}}
\def\gE{{\mathcal{E}}}
\def\gF{{\mathcal{F}}}
\def\gG{{\mathcal{G}}}
\def\gH{{\mathcal{H}}}
\def\gI{{\mathcal{I}}}
\def\gJ{{\mathcal{J}}}
\def\gK{{\mathcal{K}}}
\def\gL{{\mathcal{L}}}
\def\gM{{\mathcal{M}}}
\def\gN{{\mathcal{N}}}
\def\gO{{\mathcal{O}}}
\def\gP{{\mathcal{P}}}
\def\gQ{{\mathcal{Q}}}
\def\gR{{\mathcal{R}}}
\def\gS{{\mathcal{S}}}
\def\gT{{\mathcal{T}}}
\def\gU{{\mathcal{U}}}
\def\gV{{\mathcal{V}}}
\def\gW{{\mathcal{W}}}
\def\gX{{\mathcal{X}}}
\def\gY{{\mathcal{Y}}}
\def\gZ{{\mathcal{Z}}}
% Sets
\def\sA{{\mathbb{A}}}
\def\sB{{\mathbb{B}}}
\def\sC{{\mathbb{C}}}
\def\sD{{\mathbb{D}}}
% Don't use a set called E, because this would be the same as our symbol
% for expectation.
\def\sF{{\mathbb{F}}}
\def\sG{{\mathbb{G}}}
\def\sH{{\mathbb{H}}}
\def\sI{{\mathbb{I}}}
\def\sJ{{\mathbb{J}}}
\def\sK{{\mathbb{K}}}
\def\sL{{\mathbb{L}}}
\def\sM{{\mathbb{M}}}
\def\sN{{\mathbb{N}}}
\def\sO{{\mathbb{O}}}
\def\sP{{\mathbb{P}}}
\def\sQ{{\mathbb{Q}}}
\def\sR{{\mathbb{R}}}
\def\sS{{\mathbb{S}}}
\def\sT{{\mathbb{T}}}
\def\sU{{\mathbb{U}}}
\def\sV{{\mathbb{V}}}
\def\sW{{\mathbb{W}}}
\def\sX{{\mathbb{X}}}
\def\sY{{\mathbb{Y}}}
\def\sZ{{\mathbb{Z}}}
% Entries of a matrix
\def\emLambda{{\Lambda}}
\def\emA{{A}}
\def\emB{{B}}
\def\emC{{C}}
\def\emD{{D}}
\def\emE{{E}}
\def\emF{{F}}
\def\emG{{G}}
\def\emH{{H}}
\def\emI{{I}}
\def\emJ{{J}}
\def\emK{{K}}
\def\emL{{L}}
\def\emM{{M}}
\def\emN{{N}}
\def\emO{{O}}
\def\emP{{P}}
\def\emQ{{Q}}
\def\emR{{R}}
\def\emS{{S}}
\def\emT{{T}}
\def\emU{{U}}
\def\emV{{V}}
\def\emW{{W}}
\def\emX{{X}}
\def\emY{{Y}}
\def\emZ{{Z}}
\def\emSigma{{\Sigma}}
% entries of a tensor
% Same font as tensor, without \bm wrapper
\newcommand{\etens}[1]{\mathsfit{#1}}
\def\etLambda{{\etens{\Lambda}}}
\def\etA{{\etens{A}}}
\def\etB{{\etens{B}}}
\def\etC{{\etens{C}}}
\def\etD{{\etens{D}}}
\def\etE{{\etens{E}}}
\def\etF{{\etens{F}}}
\def\etG{{\etens{G}}}
\def\etH{{\etens{H}}}
\def\etI{{\etens{I}}}
\def\etJ{{\etens{J}}}
\def\etK{{\etens{K}}}
\def\etL{{\etens{L}}}
\def\etM{{\etens{M}}}
\def\etN{{\etens{N}}}
\def\etO{{\etens{O}}}
\def\etP{{\etens{P}}}
\def\etQ{{\etens{Q}}}
\def\etR{{\etens{R}}}
\def\etS{{\etens{S}}}
\def\etT{{\etens{T}}}
\def\etU{{\etens{U}}}
\def\etV{{\etens{V}}}
\def\etW{{\etens{W}}}
\def\etX{{\etens{X}}}
\def\etY{{\etens{Y}}}
\def\etZ{{\etens{Z}}}
% The true underlying data generating distribution
\newcommand{\pdata}{p_{\rm{data}}}
% The empirical distribution defined by the training set
\newcommand{\ptrain}{\hat{p}_{\rm{data}}}
\newcommand{\Ptrain}{\hat{P}_{\rm{data}}}
% The model distribution
\newcommand{\pmodel}{p_{\rm{model}}}
\newcommand{\Pmodel}{P_{\rm{model}}}
\newcommand{\ptildemodel}{\tilde{p}_{\rm{model}}}
% Stochastic autoencoder distributions
\newcommand{\pencode}{p_{\rm{encoder}}}
\newcommand{\pdecode}{p_{\rm{decoder}}}
\newcommand{\precons}{p_{\rm{reconstruct}}}
\newcommand{\laplace}{\mathrm{Laplace}} % Laplace distribution
\newcommand{\E}{\mathbb{E}}
\newcommand{\Ls}{\mathcal{L}}
\newcommand{\R}{\mathbb{R}}
\newcommand{\emp}{\tilde{p}}
\newcommand{\lr}{\alpha}
\newcommand{\reg}{\lambda}
\newcommand{\rect}{\mathrm{rectifier}}
\newcommand{\softmax}{\mathrm{softmax}}
\newcommand{\sigmoid}{\sigma}
\newcommand{\softplus}{\zeta}
\newcommand{\KL}{D_{\mathrm{KL}}}
\newcommand{\Var}{\mathrm{Var}}
\newcommand{\standarderror}{\mathrm{SE}}
\newcommand{\Cov}{\mathrm{Cov}}
% Wolfram Mathworld says $L^2$ is for function spaces and $\ell^2$ is for vectors
% But then they seem to use $L^2$ for vectors throughout the site, and so does
% wikipedia.
\newcommand{\normlzero}{L^0}
\newcommand{\normlone}{L^1}
\newcommand{\normltwo}{L^2}
\newcommand{\normlp}{L^p}
\newcommand{\normmax}{L^\infty}
\newcommand{\parents}{Pa} % See usage in notation.tex. Chosen to match Daphne's book.
\DeclareMathOperator*{\argmax}{arg\,max}
\DeclareMathOperator*{\argmin}{arg\,min}
\DeclareMathOperator{\sign}{sign}
\DeclareMathOperator{\Tr}{Tr}
\let\ab\allowbreak
```
## /assets/demo/latex_proj/natbib.sty
```sty path="/assets/demo/latex_proj/natbib.sty"
%%
%% This is file `natbib.sty',
%% generated with the docstrip utility.
%%
%% The original source files were:
%%
%% natbib.dtx (with options: `package,all')
%% =============================================
%% IMPORTANT NOTICE:
%%
%% This program can be redistributed and/or modified under the terms
%% of the LaTeX Project Public License Distributed from CTAN
%% archives in directory macros/latex/base/lppl.txt; either
%% version 1 of the License, or any later version.
%%
%% This is a generated file.
%% It may not be distributed without the original source file natbib.dtx.
%%
%% Full documentation can be obtained by LaTeXing that original file.
%% Only a few abbreviated comments remain here to describe the usage.
%% =============================================
%% Copyright 1993-2009 Patrick W Daly
%% Max-Planck-Institut f\"ur Sonnensystemforschung
%% Max-Planck-Str. 2
%% D-37191 Katlenburg-Lindau
%% Germany
%% E-mail: daly@mps.mpg.de
\NeedsTeXFormat{LaTeX2e}[1995/06/01]
\ProvidesPackage{natbib}
[2009/07/16 8.31 (PWD, AO)]
% This package reimplements the LaTeX \cite command to be used for various
% citation styles, both author-year and numerical. It accepts BibTeX
% output intended for many other packages, and therefore acts as a
% general, all-purpose citation-style interface.
%
% With standard numerical .bst files, only numerical citations are
% possible. With an author-year .bst file, both numerical and
% author-year citations are possible.
%
% If author-year citations are selected, \bibitem must have one of the
% following forms:
% \bibitem[Jones et al.(1990)]{key}...
% \bibitem[Jones et al.(1990)Jones, Baker, and Williams]{key}...
% \bibitem[Jones et al., 1990]{key}...
% \bibitem[\protect\citeauthoryear{Jones, Baker, and Williams}{Jones
% et al.}{1990}]{key}...
% \bibitem[\protect\citeauthoryear{Jones et al.}{1990}]{key}...
% \bibitem[\protect\astroncite{Jones et al.}{1990}]{key}...
% \bibitem[\protect\citename{Jones et al., }1990]{key}...
% \harvarditem[Jones et al.]{Jones, Baker, and Williams}{1990}{key}...
%
% This is either to be made up manually, or to be generated by an
% appropriate .bst file with BibTeX.
% Author-year mode || Numerical mode
% Then, \citet{key} ==>> Jones et al. (1990) || Jones et al. [21]
% \citep{key} ==>> (Jones et al., 1990) || [21]
% Multiple citations as normal:
% \citep{key1,key2} ==>> (Jones et al., 1990; Smith, 1989) || [21,24]
% or (Jones et al., 1990, 1991) || [21,24]
% or (Jones et al., 1990a,b) || [21,24]
% \cite{key} is the equivalent of \citet{key} in author-year mode
% and of \citep{key} in numerical mode
% Full author lists may be forced with \citet* or \citep*, e.g.
% \citep*{key} ==>> (Jones, Baker, and Williams, 1990)
% Optional notes as:
% \citep[chap. 2]{key} ==>> (Jones et al., 1990, chap. 2)
% \citep[e.g.,][]{key} ==>> (e.g., Jones et al., 1990)
% \citep[see][pg. 34]{key}==>> (see Jones et al., 1990, pg. 34)
% (Note: in standard LaTeX, only one note is allowed, after the ref.
% Here, one note is like the standard, two make pre- and post-notes.)
% \citealt{key} ==>> Jones et al. 1990
% \citealt*{key} ==>> Jones, Baker, and Williams 1990
% \citealp{key} ==>> Jones et al., 1990
% \citealp*{key} ==>> Jones, Baker, and Williams, 1990
% Additional citation possibilities (both author-year and numerical modes)
% \citeauthor{key} ==>> Jones et al.
% \citeauthor*{key} ==>> Jones, Baker, and Williams
% \citeyear{key} ==>> 1990
% \citeyearpar{key} ==>> (1990)
% \citetext{priv. comm.} ==>> (priv. comm.)
% \citenum{key} ==>> 11 [non-superscripted]
% Note: full author lists depends on whether the bib style supports them;
% if not, the abbreviated list is printed even when full requested.
%
% For names like della Robbia at the start of a sentence, use
% \Citet{dRob98} ==>> Della Robbia (1998)
% \Citep{dRob98} ==>> (Della Robbia, 1998)
% \Citeauthor{dRob98} ==>> Della Robbia
%
%
% Citation aliasing is achieved with
% \defcitealias{key}{text}
% \citetalias{key} ==>> text
% \citepalias{key} ==>> (text)
%
% Defining the citation mode and punctual (citation style)
% \setcitestyle{<comma-separated list of keywords, same
% as the package options>}
% Example: \setcitestyle{square,semicolon}
% Alternatively:
% Use \bibpunct with 6 mandatory arguments:
% 1. opening bracket for citation
% 2. closing bracket
% 3. citation separator (for multiple citations in one \cite)
% 4. the letter n for numerical styles, s for superscripts
% else anything for author-year
% 5. punctuation between authors and date
% 6. punctuation between years (or numbers) when common authors missing
% One optional argument is the character coming before post-notes. It
% appears in square braces before all other arguments. May be left off.
% Example (and default) \bibpunct[, ]{(}{)}{;}{a}{,}{,}
%
% To make this automatic for a given bib style, named newbib, say, make
% a local configuration file, natbib.cfg, with the definition
% \newcommand{\bibstyle@newbib}{\bibpunct...}
% Then the \bibliographystyle{newbib} will cause \bibstyle@newbib to
% be called on THE NEXT LATEX RUN (via the aux file).
%
% Such preprogrammed definitions may be invoked anywhere in the text
% by calling \citestyle{newbib}. This is only useful if the style specified
% differs from that in \bibliographystyle.
%
% With \citeindextrue and \citeindexfalse, one can control whether the
% \cite commands make an automatic entry of the citation in the .idx
% indexing file. For this, \makeindex must also be given in the preamble.
%
% Package Options: (for selecting punctuation)
% round - round parentheses are used (default)
% square - square brackets are used [option]
% curly - curly braces are used {option}
% angle - angle brackets are used <option>
% semicolon - multiple citations separated by semi-colon (default)
% colon - same as semicolon, an earlier confusion
% comma - separated by comma
% authoryear - selects author-year citations (default)
% numbers- selects numerical citations
% super - numerical citations as superscripts
% sort - sorts multiple citations according to order in ref. list
% sort&compress - like sort, but also compresses numerical citations
% compress - compresses without sorting
% longnamesfirst - makes first citation full author list
% sectionbib - puts bibliography in a \section* instead of \chapter*
% merge - allows the citation key to have a * prefix,
% signifying to merge its reference with that of the previous citation.
% elide - if references are merged, repeated portions of later ones may be removed.
% mcite - recognizes and ignores the * prefix for merging.
% Punctuation so selected dominates over any predefined ones.
% Package options are called as, e.g.
% \usepackage[square,comma]{natbib}
% LaTeX the source file natbib.dtx to obtain more details
% or the file natnotes.tex for a brief reference sheet.
%-----------------------------------------------------------
\providecommand\@ifxundefined[1]{%
\ifx#1\@undefined\expandafter\@firstoftwo\else\expandafter\@secondoftwo\fi
}%
\providecommand\@ifnum[1]{%
\ifnum#1\expandafter\@firstoftwo\else\expandafter\@secondoftwo\fi
}%
\providecommand\@ifx[1]{%
\ifx#1\expandafter\@firstoftwo\else\expandafter\@secondoftwo\fi
}%
\providecommand\appdef[2]{%
\toks@\expandafter{#1}\@temptokena{#2}%
\edef#1{\the\toks@\the\@temptokena}%
}%
\@ifclassloaded{agu2001}{\PackageError{natbib}
{The agu2001 class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
\@ifclassloaded{agutex}{\PackageError{natbib}
{The AGUTeX class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
\@ifclassloaded{aguplus}{\PackageError{natbib}
{The aguplus class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
\@ifclassloaded{nlinproc}{\PackageError{natbib}
{The nlinproc class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
\@ifclassloaded{egs}{\PackageError{natbib}
{The egs class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
\@ifclassloaded{egu}{\PackageError{natbib}
{The egu class already includes natbib coding,\MessageBreak
so you should not add it explicitly}
{Type <Return> for now, but then later remove\MessageBreak
the command \protect\usepackage{natbib} from the document}
\endinput}{}
% Define citation punctuation for some author-year styles
% One may add and delete at this point
% Or put additions into local configuration file natbib.cfg
\newcommand\bibstyle@chicago{\bibpunct{(}{)}{;}{a}{,}{,}}
\newcommand\bibstyle@named{\bibpunct{[}{]}{;}{a}{,}{,}}
\newcommand\bibstyle@agu{\bibpunct{[}{]}{;}{a}{,}{,~}}%Amer. Geophys. Union
\newcommand\bibstyle@copernicus{\bibpunct{(}{)}{;}{a}{,}{,}}%Copernicus Publications
\let\bibstyle@egu=\bibstyle@copernicus
\let\bibstyle@egs=\bibstyle@copernicus
\newcommand\bibstyle@agsm{\bibpunct{(}{)}{,}{a}{}{,}\gdef\harvardand{\&}}
\newcommand\bibstyle@kluwer{\bibpunct{(}{)}{,}{a}{}{,}\gdef\harvardand{\&}}
\newcommand\bibstyle@dcu{\bibpunct{(}{)}{;}{a}{;}{,}\gdef\harvardand{and}}
\newcommand\bibstyle@aa{\bibpunct{(}{)}{;}{a}{}{,}} %Astronomy & Astrophysics
\newcommand\bibstyle@pass{\bibpunct{(}{)}{;}{a}{,}{,}}%Planet. & Space Sci
\newcommand\bibstyle@anngeo{\bibpunct{(}{)}{;}{a}{,}{,}}%Annales Geophysicae
\newcommand\bibstyle@nlinproc{\bibpunct{(}{)}{;}{a}{,}{,}}%Nonlin.Proc.Geophys.
% Define citation punctuation for some numerical styles
\newcommand\bibstyle@cospar{\bibpunct{/}{/}{,}{n}{}{}%
\gdef\bibnumfmt##1{##1.}}
\newcommand\bibstyle@esa{\bibpunct{(Ref.~}{)}{,}{n}{}{}%
\gdef\bibnumfmt##1{##1.\hspace{1em}}}
\newcommand\bibstyle@nature{\bibpunct{}{}{,}{s}{}{\textsuperscript{,}}%
\gdef\bibnumfmt##1{##1.}}
% The standard LaTeX styles
\newcommand\bibstyle@plain{\bibpunct{[}{]}{,}{n}{}{,}}
\let\bibstyle@alpha=\bibstyle@plain
\let\bibstyle@abbrv=\bibstyle@plain
\let\bibstyle@unsrt=\bibstyle@plain
% The author-year modifications of the standard styles
\newcommand\bibstyle@plainnat{\bibpunct{[}{]}{,}{a}{,}{,}}
\let\bibstyle@abbrvnat=\bibstyle@plainnat
\let\bibstyle@unsrtnat=\bibstyle@plainnat
\newif\ifNAT@numbers \NAT@numbersfalse
\newif\ifNAT@super \NAT@superfalse
\let\NAT@merge\z@
\DeclareOption{numbers}{\NAT@numberstrue
\ExecuteOptions{square,comma,nobibstyle}}
\DeclareOption{super}{\NAT@supertrue\NAT@numberstrue
\renewcommand\NAT@open{}\renewcommand\NAT@close{}
\ExecuteOptions{nobibstyle}}
\DeclareOption{authoryear}{\NAT@numbersfalse
\ExecuteOptions{round,semicolon,bibstyle}}
\DeclareOption{round}{%
\renewcommand\NAT@open{(} \renewcommand\NAT@close{)}
\ExecuteOptions{nobibstyle}}
\DeclareOption{square}{%
\renewcommand\NAT@open{[} \renewcommand\NAT@close{]}
\ExecuteOptions{nobibstyle}}
\DeclareOption{angle}{%
\renewcommand\NAT@open{{{contextString}}lt;$} \renewcommand\NAT@close{{{contextString}}gt;$}
\ExecuteOptions{nobibstyle}}
\DeclareOption{curly}{%
\renewcommand\NAT@open{\{} \renewcommand\NAT@close{\}}
\ExecuteOptions{nobibstyle}}
\DeclareOption{comma}{\renewcommand\NAT@sep{,}
\ExecuteOptions{nobibstyle}}
\DeclareOption{semicolon}{\renewcommand\NAT@sep{;}
\ExecuteOptions{nobibstyle}}
\DeclareOption{colon}{\ExecuteOptions{semicolon}}
\DeclareOption{nobibstyle}{\let\bibstyle=\@gobble}
\DeclareOption{bibstyle}{\let\bibstyle=\@citestyle}
\newif\ifNAT@openbib \NAT@openbibfalse
\DeclareOption{openbib}{\NAT@openbibtrue}
\DeclareOption{sectionbib}{\def\NAT@sectionbib{on}}
\def\NAT@sort{\z@}
\def\NAT@cmprs{\z@}
\DeclareOption{sort}{\def\NAT@sort{\@ne}}
\DeclareOption{compress}{\def\NAT@cmprs{\@ne}}
\DeclareOption{sort&compress}{\def\NAT@sort{\@ne}\def\NAT@cmprs{\@ne}}
\DeclareOption{mcite}{\let\NAT@merge\@ne}
\DeclareOption{merge}{\@ifnum{\NAT@merge<\tw@}{\let\NAT@merge\tw@}{}}
\DeclareOption{elide}{\@ifnum{\NAT@merge<\thr@@}{\let\NAT@merge\thr@@}{}}
\@ifpackageloaded{cite}{\PackageWarningNoLine{natbib}
{The `cite' package should not be used\MessageBreak
with natbib. Use option `sort' instead}\ExecuteOptions{sort}}{}
\@ifpackageloaded{mcite}{\PackageWarningNoLine{natbib}
{The `mcite' package should not be used\MessageBreak
with natbib. Use option `merge' instead}\ExecuteOptions{merge}}{}
\@ifpackageloaded{citeref}{\PackageError{natbib}
{The `citeref' package must be loaded after natbib}%
{Move \protect\usepackage{citeref} to after \string\usepackage{natbib}}}{}
\newif\ifNAT@longnames\NAT@longnamesfalse
\DeclareOption{longnamesfirst}{\NAT@longnamestrue}
\DeclareOption{nonamebreak}{\def\NAT@nmfmt#1{\mbox{\NAT@up#1}}}
\def\NAT@nmfmt#1{{\NAT@up#1}}
\renewcommand\bibstyle[1]{\csname bibstyle@#1\endcsname}
\AtBeginDocument{\global\let\bibstyle=\@gobble}
\let\@citestyle\bibstyle
\newcommand\citestyle[1]{\@citestyle{#1}\let\bibstyle\@gobble}
\newcommand\bibpunct[7][, ]%
{\gdef\NAT@open{#2}\gdef\NAT@close{#3}\gdef
\NAT@sep{#4}\global\NAT@numbersfalse
\ifx #5n\global\NAT@numberstrue\global\NAT@superfalse
\else
\ifx #5s\global\NAT@numberstrue\global\NAT@supertrue
\fi\fi
\gdef\NAT@aysep{#6}\gdef\NAT@yrsep{#7}%
\gdef\NAT@cmt{#1}%
\NAT@@setcites
}
\newcommand\setcitestyle[1]{
\@for\@tempa:=#1\do
{\def\@tempb{round}\ifx\@tempa\@tempb
\renewcommand\NAT@open{(}\renewcommand\NAT@close{)}\fi
\def\@tempb{square}\ifx\@tempa\@tempb
\renewcommand\NAT@open{[}\renewcommand\NAT@close{]}\fi
\def\@tempb{angle}\ifx\@tempa\@tempb
\renewcommand\NAT@open{{{contextString}}lt;$}\renewcommand\NAT@close{{{contextString}}gt;$}\fi
\def\@tempb{curly}\ifx\@tempa\@tempb
\renewcommand\NAT@open{\{}\renewcommand\NAT@close{\}}\fi
\def\@tempb{semicolon}\ifx\@tempa\@tempb
\renewcommand\NAT@sep{;}\fi
\def\@tempb{colon}\ifx\@tempa\@tempb
\renewcommand\NAT@sep{;}\fi
\def\@tempb{comma}\ifx\@tempa\@tempb
\renewcommand\NAT@sep{,}\fi
\def\@tempb{authoryear}\ifx\@tempa\@tempb
\NAT@numbersfalse\fi
\def\@tempb{numbers}\ifx\@tempa\@tempb
\NAT@numberstrue\NAT@superfalse\fi
\def\@tempb{super}\ifx\@tempa\@tempb
\NAT@numberstrue\NAT@supertrue\fi
\expandafter\NAT@find@eq\@tempa=\relax\@nil
\if\@tempc\relax\else
\expandafter\NAT@rem@eq\@tempc
\def\@tempb{open}\ifx\@tempa\@tempb
\xdef\NAT@open{\@tempc}\fi
\def\@tempb{close}\ifx\@tempa\@tempb
\xdef\NAT@close{\@tempc}\fi
\def\@tempb{aysep}\ifx\@tempa\@tempb
\xdef\NAT@aysep{\@tempc}\fi
\def\@tempb{yysep}\ifx\@tempa\@tempb
\xdef\NAT@yrsep{\@tempc}\fi
\def\@tempb{notesep}\ifx\@tempa\@tempb
\xdef\NAT@cmt{\@tempc}\fi
\def\@tempb{citesep}\ifx\@tempa\@tempb
\xdef\NAT@sep{\@tempc}\fi
\fi
}%
\NAT@@setcites
}
\def\NAT@find@eq#1=#2\@nil{\def\@tempa{#1}\def\@tempc{#2}}
\def\NAT@rem@eq#1={\def\@tempc{#1}}
\def\NAT@@setcites{\global\let\bibstyle\@gobble}
\AtBeginDocument{\let\NAT@@setcites\NAT@set@cites}
\newcommand\NAT@open{(} \newcommand\NAT@close{)}
\newcommand\NAT@sep{;}
\ProcessOptions
\newcommand\NAT@aysep{,} \newcommand\NAT@yrsep{,}
\newcommand\NAT@cmt{, }
\newcommand\NAT@cite%
[3]{\ifNAT@swa\NAT@@open\if*#2*\else#2\NAT@spacechar\fi
#1\if*#3*\else\NAT@cmt#3\fi\NAT@@close\else#1\fi\endgroup}
\newcommand\NAT@citenum%
[3]{\ifNAT@swa\NAT@@open\if*#2*\else#2\NAT@spacechar\fi
#1\if*#3*\else\NAT@cmt#3\fi\NAT@@close\else#1\fi\endgroup}
\newcommand\NAT@citesuper[3]{\ifNAT@swa
\if*#2*\else#2\NAT@spacechar\fi
\unskip\kern\p@\textsuperscript{\NAT@@open#1\NAT@@close}%
\if*#3*\else\NAT@spacechar#3\fi\else #1\fi\endgroup}
\providecommand\textsuperscript[1]{\mbox{$^{\mbox{\scriptsize#1}}$}}
\begingroup \catcode`\_=8
\gdef\NAT@ifcat@num#1{%
\ifcat_\ifnum\z@<0#1_\else A\fi
\expandafter\@firstoftwo
\else
\expandafter\@secondoftwo
\fi
}%
\endgroup
\providecommand\@firstofone[1]{#1}
\newcommand\NAT@citexnum{}
\def\NAT@citexnum[#1][#2]#3{%
\NAT@reset@parser
\NAT@sort@cites{#3}%
\NAT@reset@citea
\@cite{\def\NAT@num{-1}\let\NAT@last@yr\relax\let\NAT@nm\@empty
\@for\@citeb:=\NAT@cite@list\do
{\@safe@activestrue
\edef\@citeb{\expandafter\@firstofone\@citeb\@empty}%
\@safe@activesfalse
\@ifundefined{b@\@citeb\@extra@b@citeb}{%
{\reset@font\bfseries?}
\NAT@citeundefined\PackageWarning{natbib}%
{Citation `\@citeb' on page \thepage \space undefined}}%
{\let\NAT@last@num\NAT@num\let\NAT@last@nm\NAT@nm
\NAT@parse{\@citeb}%
\ifNAT@longnames\@ifundefined{bv@\@citeb\@extra@b@citeb}{%
\let\NAT@name=\NAT@all@names
\global\@namedef{bv@\@citeb\@extra@b@citeb}{}}{}%
\fi
\ifNAT@full\let\NAT@nm\NAT@all@names\else
\let\NAT@nm\NAT@name\fi
\ifNAT@swa
\@ifnum{\NAT@ctype>\@ne}{%
\@citea
\NAT@hyper@{\@ifnum{\NAT@ctype=\tw@}{\NAT@test{\NAT@ctype}}{\NAT@alias}}%
}{%
\@ifnum{\NAT@cmprs>\z@}{%
\NAT@ifcat@num\NAT@num
{\let\NAT@nm=\NAT@num}%
{\def\NAT@nm{-2}}%
\NAT@ifcat@num\NAT@last@num
{\@tempcnta=\NAT@last@num\relax}%
{\@tempcnta\m@ne}%
\@ifnum{\NAT@nm=\@tempcnta}{%
\@ifnum{\NAT@merge>\@ne}{}{\NAT@last@yr@mbox}%
}{%
\advance\@tempcnta by\@ne
\@ifnum{\NAT@nm=\@tempcnta}{%
\ifx\NAT@last@yr\relax
\def@NAT@last@yr{\@citea}%
\else
\def@NAT@last@yr{--\NAT@penalty}%
\fi
}{%
\NAT@last@yr@mbox
}%
}%
}{%
\@tempswatrue
\@ifnum{\NAT@merge>\@ne}{\@ifnum{\NAT@last@num=\NAT@num\relax}{\@tempswafalse}{}}{}%
\if@tempswa\NAT@citea@mbox\fi
}%
}%
\NAT@def@citea
\else
\ifcase\NAT@ctype
\ifx\NAT@last@nm\NAT@nm \NAT@yrsep\NAT@penalty\NAT@space\else
\@citea \NAT@test{\@ne}\NAT@spacechar\NAT@mbox{\NAT@super@kern\NAT@@open}%
\fi
\if*#1*\else#1\NAT@spacechar\fi
\NAT@mbox{\NAT@hyper@{{\citenumfont{\NAT@num}}}}%
\NAT@def@citea@box
\or
\NAT@hyper@citea@space{\NAT@test{\NAT@ctype}}%
\or
\NAT@hyper@citea@space{\NAT@test{\NAT@ctype}}%
\or
\NAT@hyper@citea@space\NAT@alias
\fi
\fi
}%
}%
\@ifnum{\NAT@cmprs>\z@}{\NAT@last@yr}{}%
\ifNAT@swa\else
\@ifnum{\NAT@ctype=\z@}{%
\if*#2*\else\NAT@cmt#2\fi
}{}%
\NAT@mbox{\NAT@@close}%
\fi
}{#1}{#2}%
}%
\def\NAT@citea@mbox{%
\@citea\mbox{\NAT@hyper@{{\citenumfont{\NAT@num}}}}%
}%
\def\NAT@hyper@#1{%
\hyper@natlinkstart{\@citeb\@extra@b@citeb}#1\hyper@natlinkend
}%
\def\NAT@hyper@citea#1{%
\@citea
\NAT@hyper@{#1}%
\NAT@def@citea
}%
\def\NAT@hyper@citea@space#1{%
\@citea
\NAT@hyper@{#1}%
\NAT@def@citea@space
}%
\def\def@NAT@last@yr#1{%
\protected@edef\NAT@last@yr{%
#1%
\noexpand\mbox{%
\noexpand\hyper@natlinkstart{\@citeb\@extra@b@citeb}%
{\noexpand\citenumfont{\NAT@num}}%
\noexpand\hyper@natlinkend
}%
}%
}%
\def\NAT@last@yr@mbox{%
\NAT@last@yr\let\NAT@last@yr\relax
\NAT@citea@mbox
}%
\newcommand\NAT@test[1]{%
\@ifnum{#1=\@ne}{%
\ifx\NAT@nm\NAT@noname
\begingroup\reset@font\bfseries(author?)\endgroup
\PackageWarning{natbib}{%
Author undefined for citation`\@citeb' \MessageBreak on page \thepage%
}%
\else \NAT@nm
\fi
}{%
\if\relax\NAT@date\relax
\begingroup\reset@font\bfseries(year?)\endgroup
\PackageWarning{natbib}{%
Year undefined for citation`\@citeb' \MessageBreak on page \thepage%
}%
\else \NAT@date
\fi
}%
}%
\let\citenumfont=\@empty
\newcommand\NAT@citex{}
\def\NAT@citex%
[#1][#2]#3{%
\NAT@reset@parser
\NAT@sort@cites{#3}%
\NAT@reset@citea
\@cite{\let\NAT@nm\@empty\let\NAT@year\@empty
\@for\@citeb:=\NAT@cite@list\do
{\@safe@activestrue
\edef\@citeb{\expandafter\@firstofone\@citeb\@empty}%
\@safe@activesfalse
\@ifundefined{b@\@citeb\@extra@b@citeb}{\@citea%
{\reset@font\bfseries ?}\NAT@citeundefined
\PackageWarning{natbib}%
{Citation `\@citeb' on page \thepage \space undefined}\def\NAT@date{}}%
{\let\NAT@last@nm=\NAT@nm\let\NAT@last@yr=\NAT@year
\NAT@parse{\@citeb}%
\ifNAT@longnames\@ifundefined{bv@\@citeb\@extra@b@citeb}{%
\let\NAT@name=\NAT@all@names
\global\@namedef{bv@\@citeb\@extra@b@citeb}{}}{}%
\fi
\ifNAT@full\let\NAT@nm\NAT@all@names\else
\let\NAT@nm\NAT@name\fi
\ifNAT@swa\ifcase\NAT@ctype
\if\relax\NAT@date\relax
\@citea\NAT@hyper@{\NAT@nmfmt{\NAT@nm}\NAT@date}%
\else
\ifx\NAT@last@nm\NAT@nm\NAT@yrsep
\ifx\NAT@last@yr\NAT@year
\def\NAT@temp{{?}}%
\ifx\NAT@temp\NAT@exlab\PackageWarningNoLine{natbib}%
{Multiple citation on page \thepage: same authors and
year\MessageBreak without distinguishing extra
letter,\MessageBreak appears as question mark}\fi
\NAT@hyper@{\NAT@exlab}%
\else\unskip\NAT@spacechar
\NAT@hyper@{\NAT@date}%
\fi
\else
\@citea\NAT@hyper@{%
\NAT@nmfmt{\NAT@nm}%
\hyper@natlinkbreak{%
\NAT@aysep\NAT@spacechar}{\@citeb\@extra@b@citeb
}%
\NAT@date
}%
\fi
\fi
\or\@citea\NAT@hyper@{\NAT@nmfmt{\NAT@nm}}%
\or\@citea\NAT@hyper@{\NAT@date}%
\or\@citea\NAT@hyper@{\NAT@alias}%
\fi \NAT@def@citea
\else
\ifcase\NAT@ctype
\if\relax\NAT@date\relax
\@citea\NAT@hyper@{\NAT@nmfmt{\NAT@nm}}%
\else
\ifx\NAT@last@nm\NAT@nm\NAT@yrsep
\ifx\NAT@last@yr\NAT@year
\def\NAT@temp{{?}}%
\ifx\NAT@temp\NAT@exlab\PackageWarningNoLine{natbib}%
{Multiple citation on page \thepage: same authors and
year\MessageBreak without distinguishing extra
letter,\MessageBreak appears as question mark}\fi
\NAT@hyper@{\NAT@exlab}%
\else
\unskip\NAT@spacechar
\NAT@hyper@{\NAT@date}%
\fi
\else
\@citea\NAT@hyper@{%
\NAT@nmfmt{\NAT@nm}%
\hyper@natlinkbreak{\NAT@spacechar\NAT@@open\if*#1*\else#1\NAT@spacechar\fi}%
{\@citeb\@extra@b@citeb}%
\NAT@date
}%
\fi
\fi
\or\@citea\NAT@hyper@{\NAT@nmfmt{\NAT@nm}}%
\or\@citea\NAT@hyper@{\NAT@date}%
\or\@citea\NAT@hyper@{\NAT@alias}%
\fi
\if\relax\NAT@date\relax
\NAT@def@citea
\else
\NAT@def@citea@close
\fi
\fi
}}\ifNAT@swa\else\if*#2*\else\NAT@cmt#2\fi
\if\relax\NAT@date\relax\else\NAT@@close\fi\fi}{#1}{#2}}
\def\NAT@spacechar{\ }%
\def\NAT@separator{\NAT@sep\NAT@penalty}%
\def\NAT@reset@citea{\c@NAT@ctr\@ne\let\@citea\@empty}%
\def\NAT@def@citea{\def\@citea{\NAT@separator\NAT@space}}%
\def\NAT@def@citea@space{\def\@citea{\NAT@separator\NAT@spacechar}}%
\def\NAT@def@citea@close{\def\@citea{\NAT@@close\NAT@separator\NAT@space}}%
\def\NAT@def@citea@box{\def\@citea{\NAT@mbox{\NAT@@close}\NAT@separator\NAT@spacechar}}%
\newif\ifNAT@par \NAT@partrue
\newcommand\NAT@@open{\ifNAT@par\NAT@open\fi}
\newcommand\NAT@@close{\ifNAT@par\NAT@close\fi}
\newcommand\NAT@alias{\@ifundefined{al@\@citeb\@extra@b@citeb}{%
{\reset@font\bfseries(alias?)}\PackageWarning{natbib}
{Alias undefined for citation `\@citeb'
\MessageBreak on page \thepage}}{\@nameuse{al@\@citeb\@extra@b@citeb}}}
\let\NAT@up\relax
\newcommand\NAT@Up[1]{{\let\protect\@unexpandable@protect\let~\relax
\expandafter\NAT@deftemp#1}\expandafter\NAT@UP\NAT@temp}
\newcommand\NAT@deftemp[1]{\xdef\NAT@temp{#1}}
\newcommand\NAT@UP[1]{\let\@tempa\NAT@UP\ifcat a#1\MakeUppercase{#1}%
\let\@tempa\relax\else#1\fi\@tempa}
\newcommand\shortcites[1]{%
\@bsphack\@for\@citeb:=#1\do
{\@safe@activestrue
\edef\@citeb{\expandafter\@firstofone\@citeb\@empty}%
\@safe@activesfalse
\global\@namedef{bv@\@citeb\@extra@b@citeb}{}}\@esphack}
\newcommand\NAT@biblabel[1]{\hfill}
\newcommand\NAT@biblabelnum[1]{\bibnumfmt{#1}}
\let\bibnumfmt\@empty
\providecommand\@biblabel[1]{[#1]}
\AtBeginDocument{\ifx\bibnumfmt\@empty\let\bibnumfmt\@biblabel\fi}
\newcommand\NAT@bibsetnum[1]{\settowidth\labelwidth{\@biblabel{#1}}%
\setlength{\leftmargin}{\labelwidth}\addtolength{\leftmargin}{\labelsep}%
\setlength{\itemsep}{\bibsep}\setlength{\parsep}{\z@}%
\ifNAT@openbib
\addtolength{\leftmargin}{\bibindent}%
\setlength{\itemindent}{-\bibindent}%
\setlength{\listparindent}{\itemindent}%
\setlength{\parsep}{0pt}%
\fi
}
\newlength{\bibhang}
\setlength{\bibhang}{1em}
\newlength{\bibsep}
{\@listi \global\bibsep\itemsep \global\advance\bibsep by\parsep}
\newcommand\NAT@bibsetup%
[1]{\setlength{\leftmargin}{\bibhang}\setlength{\itemindent}{-\leftmargin}%
\setlength{\itemsep}{\bibsep}\setlength{\parsep}{\z@}}
\newcommand\NAT@set@cites{%
\ifNAT@numbers
\ifNAT@super \let\@cite\NAT@citesuper
\def\NAT@mbox##1{\unskip\nobreak\textsuperscript{##1}}%
\let\citeyearpar=\citeyear
\let\NAT@space\relax
\def\NAT@super@kern{\kern\p@}%
\else
\let\NAT@mbox=\mbox
\let\@cite\NAT@citenum
\let\NAT@space\NAT@spacechar
\let\NAT@super@kern\relax
\fi
\let\@citex\NAT@citexnum
\let\@biblabel\NAT@biblabelnum
\let\@bibsetup\NAT@bibsetnum
\renewcommand\NAT@idxtxt{\NAT@name\NAT@spacechar\NAT@open\NAT@num\NAT@close}%
\def\natexlab##1{}%
\def\NAT@penalty{\penalty\@m}%
\else
\let\@cite\NAT@cite
\let\@citex\NAT@citex
\let\@biblabel\NAT@biblabel
\let\@bibsetup\NAT@bibsetup
\let\NAT@space\NAT@spacechar
\let\NAT@penalty\@empty
\renewcommand\NAT@idxtxt{\NAT@name\NAT@spacechar\NAT@open\NAT@date\NAT@close}%
\def\natexlab##1{##1}%
\fi}
\AtBeginDocument{\NAT@set@cites}
\AtBeginDocument{\ifx\SK@def\@undefined\else
\ifx\SK@cite\@empty\else
\SK@def\@citex[#1][#2]#3{\SK@\SK@@ref{#3}\SK@@citex[#1][#2]{#3}}\fi
\ifx\SK@citeauthor\@undefined\def\HAR@checkdef{}\else
\let\citeauthor\SK@citeauthor
\let\citefullauthor\SK@citefullauthor
\let\citeyear\SK@citeyear\fi
\fi}
\newif\ifNAT@full\NAT@fullfalse
\newif\ifNAT@swa
\DeclareRobustCommand\citet
{\begingroup\NAT@swafalse\let\NAT@ctype\z@\NAT@partrue
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\newcommand\NAT@citetp{\@ifnextchar[{\NAT@@citetp}{\NAT@@citetp[]}}
\newcommand\NAT@@citetp{}
\def\NAT@@citetp[#1]{\@ifnextchar[{\@citex[#1]}{\@citex[][#1]}}
\DeclareRobustCommand\citep
{\begingroup\NAT@swatrue\let\NAT@ctype\z@\NAT@partrue
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\cite
{\begingroup\let\NAT@ctype\z@\NAT@partrue\NAT@swatrue
\@ifstar{\NAT@fulltrue\NAT@cites}{\NAT@fullfalse\NAT@cites}}
\newcommand\NAT@cites{\@ifnextchar [{\NAT@@citetp}{%
\ifNAT@numbers\else
\NAT@swafalse
\fi
\NAT@@citetp[]}}
\DeclareRobustCommand\citealt
{\begingroup\NAT@swafalse\let\NAT@ctype\z@\NAT@parfalse
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\citealp
{\begingroup\NAT@swatrue\let\NAT@ctype\z@\NAT@parfalse
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\citenum
{\begingroup
\NAT@swatrue\let\NAT@ctype\z@\NAT@parfalse\let\textsuperscript\NAT@spacechar
\NAT@citexnum[][]}
\DeclareRobustCommand\citeauthor
{\begingroup\NAT@swafalse\let\NAT@ctype\@ne\NAT@parfalse
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\Citet
{\begingroup\NAT@swafalse\let\NAT@ctype\z@\NAT@partrue
\let\NAT@up\NAT@Up
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\Citep
{\begingroup\NAT@swatrue\let\NAT@ctype\z@\NAT@partrue
\let\NAT@up\NAT@Up
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\Citealt
{\begingroup\NAT@swafalse\let\NAT@ctype\z@\NAT@parfalse
\let\NAT@up\NAT@Up
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\Citealp
{\begingroup\NAT@swatrue\let\NAT@ctype\z@\NAT@parfalse
\let\NAT@up\NAT@Up
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\Citeauthor
{\begingroup\NAT@swafalse\let\NAT@ctype\@ne\NAT@parfalse
\let\NAT@up\NAT@Up
\@ifstar{\NAT@fulltrue\NAT@citetp}{\NAT@fullfalse\NAT@citetp}}
\DeclareRobustCommand\citeyear
{\begingroup\NAT@swafalse\let\NAT@ctype\tw@\NAT@parfalse\NAT@citetp}
\DeclareRobustCommand\citeyearpar
{\begingroup\NAT@swatrue\let\NAT@ctype\tw@\NAT@partrue\NAT@citetp}
\newcommand\citetext[1]{\NAT@open#1\NAT@close}
\DeclareRobustCommand\citefullauthor
{\citeauthor*}
\newcommand\defcitealias[2]{%
\@ifundefined{al@#1\@extra@b@citeb}{}
{\PackageWarning{natbib}{Overwriting existing alias for citation #1}}
\@namedef{al@#1\@extra@b@citeb}{#2}}
\DeclareRobustCommand\citetalias{\begingroup
\NAT@swafalse\let\NAT@ctype\thr@@\NAT@parfalse\NAT@citetp}
\DeclareRobustCommand\citepalias{\begingroup
\NAT@swatrue\let\NAT@ctype\thr@@\NAT@partrue\NAT@citetp}
\renewcommand\nocite[1]{\@bsphack
\@for\@citeb:=#1\do{%
\@safe@activestrue
\edef\@citeb{\expandafter\@firstofone\@citeb\@empty}%
\@safe@activesfalse
\if@filesw\immediate\write\@auxout{\string\citation{\@citeb}}\fi
\if*\@citeb\else
\@ifundefined{b@\@citeb\@extra@b@citeb}{%
\NAT@citeundefined \PackageWarning{natbib}%
{Citation `\@citeb' undefined}}{}\fi}%
\@esphack}
\newcommand\NAT@parse[1]{%
\begingroup
\let\protect=\@unexpandable@protect
\let~\relax
\let\active@prefix=\@gobble
\edef\NAT@temp{\csname b@#1\@extra@b@citeb\endcsname}%
\aftergroup\NAT@split
\expandafter
\endgroup
\NAT@temp{}{}{}{}{}@@%
\expandafter\NAT@parse@date\NAT@date??????@@%
\ifciteindex\NAT@index\fi
}%
\def\NAT@split#1#2#3#4#5@@{%
\gdef\NAT@num{#1}\gdef\NAT@name{#3}\gdef\NAT@date{#2}%
\gdef\NAT@all@names{#4}%
\ifx\NAT@num\@empty\gdef\NAT@num{0}\fi
\ifx\NAT@noname\NAT@all@names \gdef\NAT@all@names{#3}\fi
}%
\def\NAT@reset@parser{%
\global\let\NAT@num\@empty
\global\let\NAT@name\@empty
\global\let\NAT@date\@empty
\global\let\NAT@all@names\@empty
}%
\newcommand\NAT@parse@date{}
\def\NAT@parse@date#1#2#3#4#5#6@@{%
\ifnum\the\catcode`#1=11\def\NAT@year{}\def\NAT@exlab{#1}\else
\ifnum\the\catcode`#2=11\def\NAT@year{#1}\def\NAT@exlab{#2}\else
\ifnum\the\catcode`#3=11\def\NAT@year{#1#2}\def\NAT@exlab{#3}\else
\ifnum\the\catcode`#4=11\def\NAT@year{#1#2#3}\def\NAT@exlab{#4}\else
\def\NAT@year{#1#2#3#4}\def\NAT@exlab{{#5}}\fi\fi\fi\fi}
\newcommand\NAT@index{}
\let\NAT@makeindex=\makeindex
\renewcommand\makeindex{\NAT@makeindex
\renewcommand\NAT@index{\@bsphack\begingroup
\def~{\string~}\@wrindex{\NAT@idxtxt}}}
\newcommand\NAT@idxtxt{\NAT@name\NAT@spacechar\NAT@open\NAT@date\NAT@close}
\@ifxundefined\@indexfile{}{\let\NAT@makeindex\relax\makeindex}
\newif\ifciteindex \citeindexfalse
\newcommand\citeindextype{default}
\newcommand\NAT@index@alt{{\let\protect=\noexpand\let~\relax
\xdef\NAT@temp{\NAT@idxtxt}}\expandafter\NAT@exp\NAT@temp\@nil}
\newcommand\NAT@exp{}
\def\NAT@exp#1\@nil{\index[\citeindextype]{#1}}
\AtBeginDocument{%
\@ifpackageloaded{index}{\let\NAT@index=\NAT@index@alt}{}}
\newcommand\NAT@ifcmd{\futurelet\NAT@temp\NAT@ifxcmd}
\newcommand\NAT@ifxcmd{\ifx\NAT@temp\relax\else\expandafter\NAT@bare\fi}
\def\NAT@bare#1(#2)#3(@)#4\@nil#5{%
\if @#2
\expandafter\NAT@apalk#1, , \@nil{#5}%
\else
\NAT@wrout{\the\c@NAT@ctr}{#2}{#1}{#3}{#5}%
\fi
}
\newcommand\NAT@wrout[5]{%
\if@filesw
{\let\protect\noexpand\let~\relax
\immediate
\write\@auxout{\string\bibcite{#5}{{#1}{#2}{{#3}}{{#4}}}}}\fi
\ignorespaces}
\def\NAT@noname{{}}
\renewcommand\bibitem{\@ifnextchar[{\@lbibitem}{\@lbibitem[]}}%
\let\NAT@bibitem@first@sw\@secondoftwo
\def\@lbibitem[#1]#2{%
\if\relax\@extra@b@citeb\relax\else
\@ifundefined{br@#2\@extra@b@citeb}{}{%
\@namedef{br@#2}{\@nameuse{br@#2\@extra@b@citeb}}%
}%
\fi
\@ifundefined{b@#2\@extra@b@citeb}{%
\def\NAT@num{}%
}{%
\NAT@parse{#2}%
}%
\def\NAT@tmp{#1}%
\expandafter\let\expandafter\bibitemOpen\csname NAT@b@open@#2\endcsname
\expandafter\let\expandafter\bibitemShut\csname NAT@b@shut@#2\endcsname
\@ifnum{\NAT@merge>\@ne}{%
\NAT@bibitem@first@sw{%
\@firstoftwo
}{%
\@ifundefined{NAT@b*@#2}{%
\@firstoftwo
}{%
\expandafter\def\expandafter\NAT@num\expandafter{\the\c@NAT@ctr}%
\@secondoftwo
}%
}%
}{%
\@firstoftwo
}%
{%
\global\advance\c@NAT@ctr\@ne
\@ifx{\NAT@tmp\@empty}{\@firstoftwo}{%
\@secondoftwo
}%
{%
\expandafter\def\expandafter\NAT@num\expandafter{\the\c@NAT@ctr}%
\global\NAT@stdbsttrue
}{}%
\bibitem@fin
\item[\hfil\NAT@anchor{#2}{\NAT@num}]%
\global\let\NAT@bibitem@first@sw\@secondoftwo
\NAT@bibitem@init
}%
{%
\NAT@anchor{#2}{}%
\NAT@bibitem@cont
\bibitem@fin
}%
\@ifx{\NAT@tmp\@empty}{%
\NAT@wrout{\the\c@NAT@ctr}{}{}{}{#2}%
}{%
\expandafter\NAT@ifcmd\NAT@tmp(@)(@)\@nil{#2}%
}%
}%
\def\bibitem@fin{%
\@ifxundefined\@bibstop{}{\csname bibitem@\@bibstop\endcsname}%
}%
\def\NAT@bibitem@init{%
\let\@bibstop\@undefined
}%
\def\NAT@bibitem@cont{%
\let\bibitem@Stop\bibitemStop
\let\bibitem@NoStop\bibitemContinue
}%
\def\BibitemOpen{%
\bibitemOpen
}%
\def\BibitemShut#1{%
\bibitemShut
\def\@bibstop{#1}%
\let\bibitem@Stop\bibitemStop
\let\bibitem@NoStop\bibitemNoStop
}%
\def\bibitemStop{}%
\def\bibitemNoStop{.\spacefactor\@mmm\space}%
\def\bibitemContinue{\spacefactor\@mmm\space}%
\mathchardef\@mmm=3000 %
\providecommand{\bibAnnote}[3]{%
\BibitemShut{#1}%
\def\@tempa{#3}\@ifx{\@tempa\@empty}{}{%
\begin{quotation}\noindent
\textsc{Key:}\ #2\\\textsc{Annotation:}\ \@tempa
\end{quotation}%
}%
}%
\providecommand{\bibAnnoteFile}[2]{%
\IfFileExists{#2}{%
\bibAnnote{#1}{#2}{\input{#2}}%
}{%
\bibAnnote{#1}{#2}{}%
}%
}%
\let\bibitemOpen\relax
\let\bibitemShut\relax
\def\bibfield{\@ifnum{\NAT@merge>\tw@}{\@bibfield}{\@secondoftwo}}%
\def\@bibfield#1#2{%
\begingroup
\let\Doi\@gobble
\let\bibinfo\relax
\let\restore@protect\@empty
\protected@edef\@tempa{#2}%
\aftergroup\def\aftergroup\@tempa
\expandafter\endgroup\expandafter{\@tempa}%
\expandafter\@ifx\expandafter{\csname @bib#1\endcsname\@tempa}{%
\expandafter\let\expandafter\@tempa\csname @bib@X#1\endcsname
}{%
\expandafter\let\csname @bib#1\endcsname\@tempa
\expandafter\let\expandafter\@tempa\csname @bib@Y#1\endcsname
}%
\@ifx{\@tempa\relax}{\let\@tempa\@firstofone}{}%
\@tempa{#2}%
}%
\def\bibinfo#1{%
\expandafter\let\expandafter\@tempa\csname bibinfo@X@#1\endcsname
\@ifx{\@tempa\relax}{\@firstofone}{\@tempa}%
}%
\def\@bib@Xauthor#1{\let\@bib@Xjournal\@gobble}%
\def\@bib@Xjournal#1{\begingroup\let\bibinfo@X@journal\@bib@Z@journal#1\endgroup}%
\def\@bibibid@#1{\textit{ibid}.}%
\appdef\NAT@bibitem@init{%
\let\@bibauthor \@empty
\let\@bibjournal \@empty
\let\@bib@Z@journal\@bibibid@
}%
\ifx\SK@lbibitem\@undefined\else
\let\SK@lbibitem\@lbibitem
\def\@lbibitem[#1]#2{%
\SK@lbibitem[#1]{#2}\SK@\SK@@label{#2}\ignorespaces}\fi
\newif\ifNAT@stdbst \NAT@stdbstfalse
\AtEndDocument{%
\ifNAT@stdbst\if@filesw
\immediate\write\@auxout{%
\string\providecommand\string\NAT@force@numbers{}%
\string\NAT@force@numbers
}%
\fi\fi
}
\newcommand\NAT@force@numbers{%
\ifNAT@numbers\else
\PackageError{natbib}{Bibliography not compatible with author-year
citations.\MessageBreak
Press <return> to continue in numerical citation style}
{Check the bibliography entries for non-compliant syntax,\MessageBreak
or select author-year BibTeX style, e.g. plainnat}%
\global\NAT@numberstrue\fi}
\providecommand\bibcite{}
\renewcommand\bibcite[2]{%
\@ifundefined{b@#1\@extra@binfo}{\relax}{%
\NAT@citemultiple
\PackageWarningNoLine{natbib}{Citation `#1' multiply defined}%
}%
\global\@namedef{b@#1\@extra@binfo}{#2}%
}%
\AtEndDocument{\NAT@swatrue\let\bibcite\NAT@testdef}
\newcommand\NAT@testdef[2]{%
\def\NAT@temp{#2}%
\expandafter \ifx \csname b@#1\@extra@binfo\endcsname\NAT@temp
\else
\ifNAT@swa \NAT@swafalse
\PackageWarningNoLine{natbib}{%
Citation(s) may have changed.\MessageBreak
Rerun to get citations correct%
}%
\fi
\fi
}%
\newcommand\NAT@apalk{}
\def\NAT@apalk#1, #2, #3\@nil#4{%
\if\relax#2\relax
\global\NAT@stdbsttrue
\NAT@wrout{#1}{}{}{}{#4}%
\else
\NAT@wrout{\the\c@NAT@ctr}{#2}{#1}{}{#4}%
\fi
}%
\newcommand\citeauthoryear{}
\def\citeauthoryear#1#2#3(@)(@)\@nil#4{%
\if\relax#3\relax
\NAT@wrout{\the\c@NAT@ctr}{#2}{#1}{}{#4}%
\else
\NAT@wrout{\the\c@NAT@ctr}{#3}{#2}{#1}{#4}%
\fi
}%
\newcommand\citestarts{\NAT@open}%
\newcommand\citeends{\NAT@close}%
\newcommand\betweenauthors{and}%
\newcommand\astroncite{}
\def\astroncite#1#2(@)(@)\@nil#3{%
\NAT@wrout{\the\c@NAT@ctr}{#2}{#1}{}{#3}%
}%
\newcommand\citename{}
\def\citename#1#2(@)(@)\@nil#3{\expandafter\NAT@apalk#1#2, \@nil{#3}}
\newcommand\harvarditem[4][]{%
\if\relax#1\relax
\bibitem[#2(#3)]{#4}%
\else
\bibitem[#1(#3)#2]{#4}%
\fi
}%
\newcommand\harvardleft{\NAT@open}
\newcommand\harvardright{\NAT@close}
\newcommand\harvardyearleft{\NAT@open}
\newcommand\harvardyearright{\NAT@close}
\AtBeginDocument{\providecommand{\harvardand}{and}}
\newcommand\harvardurl[1]{\textbf{URL:} \textit{#1}}
\providecommand\bibsection{}
\@ifundefined{chapter}{%
\renewcommand\bibsection{%
\section*{\refname\@mkboth{\MakeUppercase{\refname}}{\MakeUppercase{\refname}}}%
}%
}{%
\@ifxundefined\NAT@sectionbib{%
\renewcommand\bibsection{%
\chapter*{\bibname\@mkboth{\MakeUppercase{\bibname}}{\MakeUppercase{\bibname}}}%
}%
}{%
\renewcommand\bibsection{%
\section*{\bibname\ifx\@mkboth\@gobbletwo\else\markright{\MakeUppercase{\bibname}}\fi}%
}%
}%
}%
\@ifclassloaded{amsart}{\renewcommand\bibsection{\section*{\refname}}}{}%
\@ifclassloaded{amsbook}{\renewcommand\bibsection{\chapter*{\bibname}}}{}%
\@ifxundefined\bib@heading{}{\let\bibsection\bib@heading}%
\newcounter{NAT@ctr}
\renewenvironment{thebibliography}[1]{%
\bibsection
\parindent\z@
\bibpreamble
\bibfont
\list{\@biblabel{\the\c@NAT@ctr}}{\@bibsetup{#1}\global\c@NAT@ctr\z@}%
\ifNAT@openbib
\renewcommand\newblock{\par}%
\else
\renewcommand\newblock{\hskip .11em \@plus.33em \@minus.07em}%
\fi
\sloppy\clubpenalty4000\widowpenalty4000
\sfcode`\.\@m
\let\NAT@bibitem@first@sw\@firstoftwo
\let\citeN\cite \let\shortcite\cite
\let\citeasnoun\cite
}{%
\bibitem@fin
\bibpostamble
\def\@noitemerr{%
\PackageWarning{natbib}{Empty `thebibliography' environment}%
}%
\endlist
\bibcleanup
}%
\let\bibfont\@empty
\let\bibpreamble\@empty
\let\bibpostamble\@empty
\def\bibcleanup{\vskip-\lastskip}%
\providecommand\reset@font{\relax}
\providecommand\bibname{Bibliography}
\providecommand\refname{References}
\newcommand\NAT@citeundefined{\gdef \NAT@undefined {%
\PackageWarningNoLine{natbib}{There were undefined citations}}}
\let \NAT@undefined \relax
\newcommand\NAT@citemultiple{\gdef \NAT@multiple {%
\PackageWarningNoLine{natbib}{There were multiply defined citations}}}
\let \NAT@multiple \relax
\AtEndDocument{\NAT@undefined\NAT@multiple}
\providecommand\@mkboth[2]{}
\providecommand\MakeUppercase{\uppercase}
\providecommand{\@extra@b@citeb}{}
\gdef\@extra@binfo{}
\def\NAT@anchor#1#2{%
\hyper@natanchorstart{#1\@extra@b@citeb}%
\def\@tempa{#2}\@ifx{\@tempa\@empty}{}{\@biblabel{#2}}%
\hyper@natanchorend
}%
\providecommand\hyper@natanchorstart[1]{}%
\providecommand\hyper@natanchorend{}%
\providecommand\hyper@natlinkstart[1]{}%
\providecommand\hyper@natlinkend{}%
\providecommand\hyper@natlinkbreak[2]{#1}%
\AtBeginDocument{%
\@ifpackageloaded{babel}{%
\let\org@@citex\@citex}{}}
\providecommand\@safe@activestrue{}%
\providecommand\@safe@activesfalse{}%
\newcommand\NAT@sort@cites[1]{%
\let\NAT@cite@list\@empty
\@for\@citeb:=#1\do{\expandafter\NAT@star@cite\@citeb\@@}%
\if@filesw
\expandafter\immediate\expandafter\write\expandafter\@auxout
\expandafter{\expandafter\string\expandafter\citation\expandafter{\NAT@cite@list}}%
\fi
\@ifnum{\NAT@sort>\z@}{%
\expandafter\NAT@sort@cites@\expandafter{\NAT@cite@list}%
}{}%
}%
\def\NAT@star@cite{%
\let\NAT@star@sw\@secondoftwo
\@ifnum{\NAT@merge>\z@}{%
\@ifnextchar*{%
\let\NAT@star@sw\@firstoftwo
\NAT@star@cite@star
}{%
\NAT@star@cite@nostar
}%
}{%
\NAT@star@cite@noextension
}%
}%
\def\NAT@star@cite@star*{%
\NAT@star@cite@nostar
}%
\def\NAT@star@cite@nostar{%
\let\nat@keyopt@open\@empty
\let\nat@keyopt@shut\@empty
\@ifnextchar[{\NAT@star@cite@pre}{\NAT@star@cite@pre[]}%
}%
\def\NAT@star@cite@pre[#1]{%
\def\nat@keyopt@open{#1}%
\@ifnextchar[{\NAT@star@cite@post}{\NAT@star@cite@post[]}%
}%
\def\NAT@star@cite@post[#1]#2\@@{%
\def\nat@keyopt@shut{#1}%
\NAT@star@sw{\expandafter\global\expandafter\let\csname NAT@b*@#2\endcsname\@empty}{}%
\NAT@cite@list@append{#2}%
}%
\def\NAT@star@cite@noextension#1\@@{%
\let\nat@keyopt@open\@empty
\let\nat@keyopt@shut\@empty
\NAT@cite@list@append{#1}%
}%
\def\NAT@cite@list@append#1{%
\edef\@citeb{\@firstofone#1\@empty}%
\if@filesw\@ifxundefined\@cprwrite{}{\expandafter\@cprwrite\@citeb=}\fi
\if\relax\nat@keyopt@open\relax\else
\global\expandafter\let\csname NAT@b@open@\@citeb\endcsname\nat@keyopt@open
\fi
\if\relax\nat@keyopt@shut\relax\else
\global\expandafter\let\csname NAT@b@shut@\@citeb\endcsname\nat@keyopt@shut
\fi
\toks@\expandafter{\NAT@cite@list}%
\ifx\NAT@cite@list\@empty
\@temptokena\expandafter{\@citeb}%
\else
\@temptokena\expandafter{\expandafter,\@citeb}%
\fi
\edef\NAT@cite@list{\the\toks@\the\@temptokena}%
}%
\newcommand\NAT@sort@cites@[1]{%
\count@\z@
\@tempcntb\m@ne
\let\@celt\delimiter
\def\NAT@num@list{}%
\let\NAT@cite@list\@empty
\let\NAT@nonsort@list\@empty
\@for \@citeb:=#1\do{\NAT@make@cite@list}%
\ifx\NAT@nonsort@list\@empty\else
\protected@edef\NAT@cite@list{\NAT@cite@list\NAT@nonsort@list}%
\fi
\ifx\NAT@cite@list\@empty\else
\protected@edef\NAT@cite@list{\expandafter\NAT@xcom\NAT@cite@list @@}%
\fi
}%
\def\NAT@make@cite@list{%
\advance\count@\@ne
\@safe@activestrue
\edef\@citeb{\expandafter\@firstofone\@citeb\@empty}%
\@safe@activesfalse
\@ifundefined{b@\@citeb\@extra@b@citeb}%
{\def\NAT@num{A}}%
{\NAT@parse{\@citeb}}%
\NAT@ifcat@num\NAT@num
{\@tempcnta\NAT@num \relax
\@ifnum{\@tempcnta<\@tempcntb}{%
\let\NAT@@cite@list=\NAT@cite@list
\let\NAT@cite@list\@empty
\begingroup\let\@celt=\NAT@celt\NAT@num@list\endgroup
\protected@edef\NAT@num@list{%
\expandafter\NAT@num@celt \NAT@num@list \@gobble @%
}%
}{%
\protected@edef\NAT@num@list{\NAT@num@list \@celt{\NAT@num}}%
\protected@edef\NAT@cite@list{\NAT@cite@list\@citeb,}%
\@tempcntb\@tempcnta
}%
}%
{\protected@edef\NAT@nonsort@list{\NAT@nonsort@list\@citeb,}}%
}%
\def\NAT@celt#1{%
\@ifnum{#1>\@tempcnta}{%
\xdef\NAT@cite@list{\NAT@cite@list\@citeb,\NAT@@cite@list}%
\let\@celt\@gobble
}{%
\expandafter\def@NAT@cite@lists\NAT@@cite@list\@@
}%
}%
\def\NAT@num@celt#1#2{%
\ifx#1\@celt
\@ifnum{#2>\@tempcnta}{%
\@celt{\number\@tempcnta}%
\@celt{#2}%
}{%
\@celt{#2}%
\expandafter\NAT@num@celt
}%
\fi
}%
\def\def@NAT@cite@lists#1,#2\@@{%
\xdef\NAT@cite@list{\NAT@cite@list#1,}%
\xdef\NAT@@cite@list{#2}%
}%
\def\NAT@nextc#1,#2@@{#1,}
\def\NAT@restc#1,#2{#2}
\def\NAT@xcom#1,@@{#1}
\InputIfFileExists{natbib.cfg}
{\typeout{Local config file natbib.cfg used}}{}
%%
%% <<<<< End of generated file <<<<<<
%%
%% End of file `natbib.sty'.
```
## /assets/demo/latex_proj/section/appendix.tex
```tex path="/assets/demo/latex_proj/section/appendix.tex"
\newcommand{\AppendixSetup}{%
\appendix
\renewcommand{\thesection}{\Alph{section}} % A/B/C...
\setcounter{tocdepth}{2}\setcounter{secnumdepth}{2}
% 章节标题样式
\titleformat{\section}{\large\bfseries\color{red}}{\thesection}{1em}{}
\titleformat{\subsection}{\normalsize\bfseries}{\thesubsection}{0.8em}{}
% 附录目录条目样式（点线 + 右对齐页码）
\titlecontents{section}
[0em]{\bfseries\color{red}}{\contentslabel{1.2em}}{}{\titlerule*[.5pc]{.}\contentspage}[\vspace{0.2em}]
\titlecontents{subsection}
[1.8em]{}{\contentslabel{1.6em}}{}{\titlerule*[.5pc]{.}\contentspage}[\vspace{0.1em}]
}
\newcommand{\AppendixTitlePage}{%
\begin{center}
\LARGE\bfseries Appendix\par
\end{center}
\vspace{0.75em}
\noindent\textbf{Contents}\par
\vspace{0.5em}
}
% ===== 第一页只放目录 =====
\clearpage
\AppendixSetup
\startcontents[app] % 开始捕获“附录目录”
\AppendixTitlePage
\printcontents[app]{l}{1}{} % 打印仅附录目录（section+subsection）
\clearpage % ← 目录页结束；正文从新页开始
% ====== 你的附录正文 ======
\section{Checklist}
\subsection{The Use of Large Language Models}
In our work, LLMs are used for following aspects:
\begin{itemize}
\item Using an LLM to help with paper writing. We use GPT5 to help optimize language, correct grammar and write {\LaTeX} table code.
\item Using an LLM as a research assistant. We use GPT5 to help search related works.
\item Using an LLM in our methods and experiment. This is described in the paper.
\end{itemize}
\subsection{Ethics Statement}
We confirm that our study did not use any sensitive data where all data are public available. We have conducted this research and reported our findings responsibly. All results are presented transparently, including both performance gains and any observed limitations. We have diligently cited all relevant prior work and data sources to give proper credit and context. By following best practices in documentation and research integrity, we aim to contribute positively to the scientific community while upholding the highest ethical standards.
\subsection{Reproducibility statement}
We are committed to ensuring the reproducibility of our results. All code and data needed to reproduce the experiments will be made publicly available. We will release this repository openly with an appropriate open-source license upon publication. The datasets used in our experiments are standard public benchmarks for language modeling and understanding (e.g., widely-used corpora and evaluation sets). These resources are readily accessible to other researchers.
% \section{PaperTalker}
% The details of repair and visual-selective MCTS layout refinement are shown in Algorithm~\ref{alg:compile-repair} and Algorithm~\ref{alg:visual-selective} respectively.
% \begin{algorithm}
% \small
% \caption{Slide Generation via Compile--Repair}
% \label{alg:compile-repair}
% \begin{algorithmic}[1]
% \Require Text source $t$; figure set $\mathcal{F}=\{f_i\}_{i=1}^{n}$; max iterations $K$
% \Ensure Compilable slide code $c^{*}$
% \State $c \gets \operatorname{LLM}(t, \mathcal{F})$ \Comment{initial draft $c^{(0)}$}
% \For{$k = 1$ \textbf{to} $K$}
% \State $(e, w) \gets \operatorname{Compile}(c)$
% \If{$e = \varnothing$}
% \State $c^{*} \gets c$; \Return $c^{*}$ \Comment{no errors; stop}
% \EndIf
% \State $c \gets \operatorname{LLM}(c, e)$ \Comment{repair using compiler errors only}
% \EndFor
% \State $c^{*} \gets c$; \Return $c^{*}$ \Comment{best-effort if max iterations reached}
% \end{algorithmic}
% \end{algorithm}
% \begin{algorithm}
% \footnotesize
% \caption{Visual-Selective Layout Refinement}
% \label{alg:visual-selective}
% \begin{algorithmic}[1]
% \Require Compilable slide code $c^*$; text font scales $\mathcal{A}_{\text{text}}$; figure font scale $\alpha_{\text{fig}}$; figure scales $\mathcal{B}$
% \Ensure Refined slide code $c^{\dagger}$ and slides $s$
% \State $(\_, w)\gets\operatorname{Compile}(c^*)$;\ \ $\mathcal{I}\gets\operatorname{OverfullFrames}(w)$
% \If{$\mathcal{I}=\varnothing$} \State \Return $c^{\dagger}\gets c^*$ \EndIf
% \For{\textbf{each } $i\in\mathcal{I}$}
% \State $s\gets\operatorname{ExtractFrame}(c^*,i)$;\ \ $\mathcal{C}\gets\varnothing$
% \If{$\operatorname{IsTextOnly}(s)$}
% \State $\mathcal{C}\gets\{\operatorname{ApplyFontScale}(s,\alpha):\alpha\in\mathcal{A}_{\text{text}}\}$
% \Else
% \State $s_{\text{font}}\gets\operatorname{ApplyFontScale}(s,\alpha_{\text{fig}})$
% \State $\mathcal{C}\gets\{s_{\text{font}}\}\ \cup\ \{\operatorname{ApplyFigureScale}(s_{\text{font}},\beta):\beta\in\mathcal{B}\}$
% \EndIf
% \State $\text{img}\gets\{\operatorname{RenderAsImage}(c \text{ with } s' \text{ at } i): s'\in\mathcal{C}\}$
% \State $s^{\star}\gets\arg\max_{s'\in\mathcal{C}}\ \operatorname{VLM\_Judge}(\text{img}[s'],\text{prompt}_{\text{layout}})$
% \State $c\gets\operatorname{ReplaceFrame}(c,i,s^{\star})$
% \EndFor
% \State $c^{\dagger}\gets c$
% \State \Return $s\gets\operatorname{CompilePDF}(c^{\dagger})$
% \end{algorithmic}
% \end{algorithm}
\section{Evaluation Metrics}
\subsection{IP Memory}
\label{sec:ip}
We propose a novel metric to evaluate how well an audience retains a work after watching its presentation video. Motivated by \textbf{real-world conference interactions}, this metric assesses whether an audience member, after viewing several presentation videos, can recall the work and pose a relevant question when meeting the author.
To operationalize this, we construct video–question pairs by sampling a five-second clip from each presentation video and selecting a corresponding understanding-level question from PresentQuiz. A VideoLLM serves as the audience proxy: it is presented with four randomly sampled video–question pairs, where the videos and questions are shuffled, together with an image of one speaker as the query. The model is then asked to identify the relevant question to pose, and the accuracy quantifies the IP Memory score. Higher recall accuracy indicates that the generated results are more impressive and hold greater potential for lasting impact.
\section{Experiment}
\subsection{Video Results}
Video results please refer to the supplementary materials.
\subsection{Results of Tree Search Visual Choice}
Figure~\ref{fig:tree_vis} illustrates the slides before and after applying tree search visual choice refinement. The refinement \textbf{resolves the overfull issues} and substantially improves slide quality, indicating that this module \textbf{plays a crucial role in layout adjustment}.
\begin{figure}[t]
\centering
\includegraphics[width=\linewidth]{figure/tree_search_vis.pdf}
\caption{\textbf{Slide Visualization of Tree Search Visual Choice.} The first row shows slide results before layout refinement, while the second row shows their corresponding slides after refinement.}
\label{fig:tree_vis}
\end{figure}
\section{Prompts}
% 颜色（可按需调整）
\definecolor{CardHeader}{RGB}{124,146,84} % 橄榄绿标题栏
\definecolor{CardHeaderDark}{RGB}{100,120,65}
\definecolor{CardFrame}{RGB}{205,210,190} % 浅绿边框
% 小圆点
\newcommand{\headerdot}{\tikz[baseline=-0.6ex]\node[circle,fill=CardHeaderDark,inner sep=1.5pt]{};}
% 卡片环境
\newtcolorbox{promptbox}[1]{%
enhanced, breakable,
colback=white, colframe=CardFrame,
boxrule=0.5pt, arc=2mm,
left=10pt,right=10pt,top=8pt,bottom=10pt,
before skip=8pt, after skip=10pt,
drop shadow=black!15,
attach boxed title to top left={xshift=1mm,yshift*=-2mm},
boxed title style={
colback=CardHeader, colframe=CardHeader, coltext=white,
boxrule=0pt, left=8pt,right=8pt,top=3pt,bottom=3pt, arc=2mm
},
title={\headerdot\ \textbf{Prompt:}~#1},
}
\begin{promptbox}{Slide Generation}
\textbf{System Prompt:} Please generate a complete English PPT introduction based on the following TeX source text content, using LaTeX Beamer. The specific requirements are as follows.
\medskip
\textbf{Content structure:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item The PPT should contain the following chapters (arranged in order), and each chapter must have a clear title and content:
\item Motivation (research background and problem statement)
\item Related work (current status and challenges in the field)
\item Method (core technical framework) [The content of the method needs to be introduced in detail, and each part of the method should be introduced on a separate page]
\item Innovation (differentiation from existing work)
\item Experimental method (experimental design and process)
\item Experimental setting (dataset, parameters, environment, etc.)
\item Experimental results (main experimental results and comparative analysis)
\item Ablation experiment (validation of the role of key modules)
\item Deficiencies (limitations of current methods)
\item Future research (improvement direction or potential application)
\item End slide (Thank you)
\end{itemize}
\textbf{Format requirements:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item Use Beamer's theme suitable for academic presentations, with simple color matching.
\item The content of each page should be concise, avoid long paragraphs, and use itemize or block environment to present points.
The title page contains the paper title, author, institution, and date.
\item Key terms or mathematical symbols are highlighted with \text{\\alert\{\}}.
\end{itemize}
\textbf{Image and table processing:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item All image paths are given, and relative paths are used when citing, the picture names must "be consistent with the name in tex file".
\item Images should automatically adapt to width, and add titles and labels
\item Experimental result tables should be extracted from the source text, formatted using tabular or booktabs environments, and marked with reference sources ( "as shown in table").
\end{itemize}
\textbf{Code generation requirements:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item The generated LaTeX code must be complete and can be compiled directly (including necessary structures).
\item Mark the source text location corresponding to each section in the code comments (for example, % corresponds to the source text Section 3.2).
\item If there are mathematical formulas in the source text, they must be retained and correctly converted to LaTeX syntax (such as $y=f(x)$).
\end{itemize}
\textbf{Other instructions:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item Image content should be read from the tex file, and the source name should be used directly without arbitrary modification. Image references should use real image names and should not be forged;
\item Table content should first extract real data from the source document.
\item All content should be in English.
\item If the source text is long, it is allowed to summarize the content, but the core methods, experimental data and conclusions must be retained.
\item To enhance readability, a transition page can be added (for example, "This section will introduce the experimental part").
\item Perfer more images than heavy text. **The number of slides should be around 10.**
\item **\& in title is not allowed which will cause error "Misplaced alignment tab character \&\"**
**Pay attention to this "error: !File ended while scanning use of \text{\\frame}\"**
\item Only output latex code which should be ready to compile using tectonic(simple verson of TeX Live). Before output check if the code is grammatically correct.
\end{itemize}
\end{promptbox}
\begin{promptbox}{Error Correction}
\textbf{System Prompt:} You are given a LaTeX Beamer code for the slides of a research paper and its error information. Correct these errors \emph{without changing} the slide content (text, figures, layout).
\medskip
\textbf{Instructions:}
\begin{itemize}
\item Apply the minimal edits required to make the file compile: add missing packages, close/open environments, balance braces, escape special characters, fix math delimiters, resolve duplicate labels, and correct obvious path or option typos.
\item Do \emph{not} paraphrase or delete text; do \emph{not} change figure/table content, captions, labels, or layout semantics.
\item Keep all image/table file names and relative paths as given; do not invent or rename assets.
\item Preserve the original Beamer theme, colors, and structure.
\item Ensure the final output compiles with \textbf{Tectonic}; close all environments and avoid undefined commands.
\end{itemize}
\medskip
\textbf{Output (strict):} Output \emph{only} the corrected LaTeX source, beginning with \texttt{beamer} and ending with \texttt{document}; no extra commentary.
\end{promptbox}
% 上面一行的说明文字（如截图左上角的粗体句子）
\begin{promptbox}{MSTS Judge}
\textbf{System Prompt:} You are a slide layout judge. You see four slides A–D in a 2×2 grid:
A (top-left), B (top-right), C (bottom-left), D (bottom-right).
\medskip
\textbf{Definitions}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item \textbf{Overfull:} any part of the figure or its caption is clipped, outside the frame, or overlapped/hidden.
\item \textbf{Coverage:} among non-overfull options, larger visible content with less empty background is better.
\item \textbf{Risk:} risk of overfull decreases from A → D (A largest, D smallest).
\item \textbf{Coverage trend:} coverage decreases from A → D.
\end{itemize}
\textbf{Rules (judge only the given images)}
\begin{enumerate}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item Disqualify any option with overfull (caption must be fully visible).
\item From the remaining, pick the one with the greatest coverage.
\item Practical method: scan \textbf{A → B → C → D}; choose the \emph{first} slide in that order that is not overfull.
\end{enumerate}
\medskip
\textbf{Output only (strict; do \emph{not} output \texttt{\`\`\`json}):}
\begin{verbatim}
{
"reason": "concise comparison",
"choice": "A" | "B" | "C" | "D"
}
\end{verbatim}
\end{promptbox}
\begin{promptbox}{Slide Script with Cursor Positions}
\textbf{System Prompt:} You are an academic researcher presenting your own work at a research conference. You are provided with a sequence of adjacent slides.
\medskip
\textbf{Instructions:}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item For each slide, write a smooth, engaging, and coherent first-person presentation script.
\item Clearly explain the \emph{current} slide with academic clarity, brevity, and completeness; use a professional, formal tone and avoid content unrelated to the paper.
\item Each sentence must include \emph{exactly one} cursor position description drawn from the \emph{current slide} and listed in order, using the format \texttt{script\;|\;cursor description}. If no cursor is needed for a sentence, write \texttt{no}.
\item Limit the total script for each slide to \textbf{50 words} or fewer.
\item Separate slides using the delimiter \texttt{\#\#\#}.
\end{itemize}
\medskip
\textbf{Output Format (strict):}
\begin{verbatim}
sentence 1 | cursor description
sentence 2 | cursor description
...
###
sentence 1 | cursor description
...
\end{verbatim}
\end{promptbox}
\begin{promptbox}{Meta Similarity}
\textbf{System Prompt:} You are an evaluator. You will be given two presentation videos of the same talk: (1) a human-presented version and (2) an AI-generated version. Evaluate \emph{only} the slides and subtitles; ignore the presenter’s face, voice quality, background music, camera motion, and any non-slide visuals.
\medskip
\textbf{Inputs You May Receive}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item Human video (and optionally its slide images and subtitles/transcript)
\item AI video (and optionally its slide images and subtitles/transcript)
\end{itemize}
\textbf{Evaluation Scope (focus strictly on slides + subtitles)}
\begin{enumerate}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item \textbf{Slide Content Matching:} Do AI slides convey the same key points and comparable layout/visual elements (titles, bullets, diagrams, tables, axes annotations) as the human version?
\item \textbf{Slide Sequence Alignment:} Is slide order consistent? Any sections missing, added, or rearranged?
\item \textbf{Subtitle Wording Similarity:} Do AI subtitles reflect similar phrasing/terminology and information as the human speech/subtitles? Focus on semantic equivalence; minor style/spelling differences do not matter.
\item \textbf{Slide–Subtitle Synchronization:} Within the AI video, does narration/subtitle content match the on-screen slide at the same time? Does this broadly align with the human presenter’s per-slide content?
\end{enumerate}
\textbf{Evidence-Only Rules}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item Base the judgment solely on the provided materials (videos, slides, subtitles). Do \emph{not} use outside knowledge.
\item If some inputs are missing (\textit{e.g.}, no subtitles), judge from what is available and briefly note the missing piece in the Reasons.
\end{itemize}
\textbf{Relaxed Scoring Rubric (0–5)}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item \textbf{5} — Nearly identical: slides and subtitles closely match the human version in content, layout, sequence, and timing; wording is near-paraphrase.
\item \textbf{4} — Highly similar: only minor layout/phrasing differences; content, order, and alignment clearly match.
\item \textbf{3} — Moderate differences yet same core content: several layout/wording/sequence deviations but main sections and key points are preserved. (Leniency: borderline cases between 2 and 3 \emph{round up} to 3.)
\item \textbf{2} — Partial overlap: substantial omissions/rearrangements or subtitle drift; multiple slide mismatches or sync issues.
\item \textbf{1} — Minimal overlap: only a few matching fragments; most slides/subtitles diverge.
\item \textbf{0} — No meaningful match: AI slides/subtitles do not correspond to the human version.
\end{itemize}
\noindent\emph{Lenient mapping: if borderline between adjacent levels, choose the higher score. If computing subscores, average and \textbf{round up} to the nearest integer in [0,5].}
\medskip
\textbf{Output Format (STRICT; exactly one line)}
\begin{verbatim}
Content Similarity: X/5; Reasons
\end{verbatim}
Where \texttt{X} is an integer 0–5 from the rubric, and \texttt{Reasons} is 1–3 short sentences referencing content, sequence, wording, and synchronization as relevant.
\end{promptbox}
\begin{promptbox}{PresentArena}
\textbf{System Prompt:} You are an expert in evaluating academic presentation videos. You are given two videos (Video A and Video B) on the same research topic. Evaluate each video independently and then decide which is better, or if they are basically the same (preferred when not confident).
\medskip
\textbf{Evaluation Criteria}
\begin{itemize}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item \textbf{Content Clarity}: Are key ideas and findings clearly explained?
\item \textbf{Speaker Delivery}: Is the speaker confident, fluent, and engaging?
\item \textbf{Visual Aids}: Are slides/visuals clear, helpful, and well-integrated?
\item \textbf{Structure \& Pacing}: Is the talk logically organized and appropriately paced?
\item \textbf{Audience Engagement}: Does the speaker maintain interest and attention?
\end{itemize}
\textbf{Steps}
\begin{enumerate}[leftmargin=1.2em,itemsep=2pt,topsep=2pt]
\item \textbf{Step 1:} Write a short (1–2 sentence) evaluation of \textbf{Video A} based on the criteria.
\item \textbf{Step 2:} Write a short (1–2 sentence) evaluation of \textbf{Video B} based on the criteria.
\item \textbf{Step 3:} Decide which video is better, or if they are basically the same (prefer ``Same'' if not confident).
\end{enumerate}
\medskip
\textbf{Output Format (Strict; only these three blocks):}
\begin{verbatim}
Step 1:
[1–2 sentences evaluating Video A]
Step 2:
[1–2 sentences evaluating Video B]
Step 3:
Final Judgment:
[A] | [B] | [Same]
Reason: [One concise sentence justifying the judgment based on Steps1-2.]
\end{verbatim}
\end{promptbox}
\begin{promptbox}{PresentationQuiz}
\textbf{System Prompt:} You are an answering agent. You will be provided with:
1) a presentation video of a paper, and 2) a JSON object called \texttt{"questions"} containing multiple questions, each with four options (A–D).
Analyze the video thoroughly and answer each question \emph{solely} based on the video content (no external knowledge). Do not reference timesteps that exceed the video length.
\medskip
\textbf{Instructions:}
\begin{itemize}
\item For each question, if the video provides sufficient evidence for a specific option (A, B, C, or D), choose that option.
\item Include a brief reference to where in the video the evidence appears (\textit{e.g.}, ``Top-left text'', ``Event date section'').
\item Rely only on the video; do not use outside context.
\item Provide an answer entry for \emph{all} questions present in \texttt{"questions"}.
\end{itemize}
\medskip
\textbf{Template (steps to follow):}
\begin{enumerate}
\item Study the presentation video together with \texttt{"questions"}.
\item For each question, determine whether the video clearly supports one of the four options; if so, pick that answer.
\item Provide a brief reference indicating where in the video you found the evidence.
\item Format the final output strictly as a JSON object with the following pattern (and no extra keys or explanations).
\end{enumerate}
\textbf{Output Format (strict):}
\begin{verbatim}
{
"Question 1": { "answer": "X", "reference": "some reference" },
"Question 2": { "answer": "X", "reference": "some reference" },
...
}
\end{verbatim}
\textbf{questions payload:}
\begin{verbatim}
{{questions}}
\end{verbatim}
\end{promptbox}
```
## /assets/demo/latex_proj/section/benchmark.tex
```tex path="/assets/demo/latex_proj/section/benchmark.tex"
% Benchmark
% task formulation
% data curation
% metrics
% Perception – [which is better] ✅
% Similarity – [video, slides+subtitle, speech] ✅
% Performance - [video QA] ✅
% Ablation experiments
% talking-head&personalized speech – [needle in a haystack] ✅
% 4 video clips + 4 qa & querry image or audio
% cursor (?)
% user study on w/o cursor, w/o talking-head, w/o personalized speech
% 导言区：
% \usepackage{graphicx}
% \usepackage{subcaption}
% 导言区：\usepackage{graphicx}\usepackage{subcaption}
% \section{\our~Benchmark}
% \begin{figure}[t]
% \centering
% \includegraphics[width=\linewidth]{figure/data_stat.pdf}
% \caption{Overview of Paer2Video benchmark.\kevin{all pdf; by three separate fig;}}
% \label{fig:data_stat}
% \end{figure}
\vspace{-0.2\baselineskip}
\section{\bench~Benchmark}
\vspace{-0.4\baselineskip}
\subsection{Task Definition}
\vspace{-0.4\baselineskip}
% \kevin{slightly longer}
Given a research paper and the author’s identity information, our goal is to automatically synthesize an academic presentation video that faithfully conveys the paper’s core contributions in an audience-friendly manner.
We identify that a perfect presentation video is usually required to integrate four coordinated components:
\textbf{(\textit{i}) slides} contain well-organized, visually oriented, expressive figures and tables with concise text description;
%\kevin{well-organized content, visually rather than dense text}
\textbf{(\textit{ii}) synchronized subtitles and speech} are semantically aligned with the slides, including supplementary details;
% \kevin{is usually not exactly the same as slide}
\textbf{(\textit{iii}) presenter} should exhibit natural yet professional facial expressions, ideally accompanied by appropriate gestures;
% \kevin{encourage to show face, sometimes gesture}
and \textbf{(\textit{iv}) a cursor indicator} serves as an attentional anchor, helping the audience focus and follow the narration.
%kevin{that anchors visual attention, helps the audience to focus}.
\vspace{-0.2\baselineskip}
This task poses several distinctive challenges:
\textbf{\textit{a}. Multi-modal Long-Context Understanding.} Research papers span many pages with dense text, equations, figures, and tables.
% Generating formal, well-structured slides with fine-grained layout requires content selection, cross-modal grounding, and fine-grained layout design.
\textbf{\textit{b}. Multi-turn Agent Tasks.} It is challenging to solve this task with a single end-to-end model, as it requires multi-channel generation and alignment (\textit{e.g.}, slides, cursors, and presenter).
%An efficient, well-designed agent system is therefore needed to address this task.
\textbf{\textit{c}. Personalized Presenter Synthesis.}
%The human presenter shapes credibility and audience engagement. However,
Achieving high-quality, identity-preserving, and lip-synchronous talking-head video remains time-consuming, and even more challenging when jointly modeling voice, face, and gesture.
\textbf{\textit{d}. Spatial-Temporal-Grounding.}
%The cursor is a crucial visual cue for the audience to follow the narrative. However,
Producing cursor trajectories synchronized with narration and slide content demands precise alignment between linguistic units and visual anchors.
% what define a good present video, require / challenges:
% 0. paper long ctx inputs
% 1. slide gen (visual layout)
% 2. text2speech ()
% 3. talking head (slow, consider mouth, hand gesture, formal)
% 4. cursor
\vspace{-0.2\baselineskip}
\subsection{Data Curation}
% non-trivial
% diversity, topics, year, paired human video
% how we combine to obtain a full video
% human filtering
% topic cv \%, nlp \%;
% percentage of with slide /without slide
\vspace{-0.2\baselineskip}
\textbf{Data Source.} We use AI conference papers as the data source for two reasons: (i) they offer high-quality, diverse content across subfields with rich text, figures, and tables; and (ii) the field’s rapid growth and open-sharing culture provide plentiful, polished author-recorded presentations and slides on YouTube and SlidesLive. However, complete metadata are often unavailable (\textit{e.g.}, presentation videos, slides, presenter images, and voice samples). We thus manually select papers with relatively complete metadata and supplement missing fields by sourcing presenter images from authors’ websites. Overall, we curate 101 peer-reviewed conference papers from the past three years: 41 from machine learning (\textit{e.g.}, NeurIPS, ICLR, ICML), 40 from computer vision (\textit{e.g.}, CVPR, ICCV, ECCV), and 20 from natural language processing(\textit{e.g.}, ACL, EMNLP, NAACL).
Each instance includes the paper’s full \LaTeX{} project and a matched, author-recorded presentation video comprising the slide and talking-head streams with speaker identity (\textit{e.g.}, portrait and voice sample). For 40\% of the data, we additionally collect the original slide files (PDF), enabling direct, reference-based evaluation of slide generation.
% \kevin{But most of paper does not pair with complete metadata (); Therefore, we manually xxx}
\vspace{-0.2\baselineskip}
\textbf{Data Statistics.}
Overall, {\bench} covers 101 paper-video pairs spanning diverse topics as shown in Figure~\ref{fig:stat} (a), ensuring broad coverage across fields. The paper contains $13.3K$ words($3.3K$ tokens), 44.7 figures, and 28.7 pages on average, serving as multi-modal long document inputs. As illustrated in Figure~\ref{fig:stat} (b) and (c), we also report the distributions of slides per presentation and video durations in {\bench}. On average, presentations contain 16 slides and last 6min~15s, with some samples reaching up to 14 minutes. Although {\bench} comprises 101 curated presentations, the benchmark is designed to evaluate long-horizon agentic tasks rather than mere video generation.
% \kevin{refer paper2poster stats.}
% \kevin{highlight human effort;}
\newcounter{sqctr}
\newcommand{\sqimg}[2]{%
\stepcounter{sqctr}%
\begin{minipage}[t]{0.31\textwidth}
\centering
\includegraphics[width=\linewidth,height=\linewidth,keepaspectratio]{#1}
\par\vspace{2pt}\small(\alph{sqctr})~#2%
\end{minipage}%
}
\begin{figure}[t]
\centering
\setcounter{sqctr}{0} % 每次图开始时清零
\sqimg{figure/paper_topics_wordcloud.pdf}{Word cloud of topics}\hfill
\sqimg{figure/slides_count_hist.pdf}{Slides per video}\hfill
\sqimg{figure/video_length_hist.pdf}{Video length}
\caption{\textbf{Statistics of {\bench} benchmark.} It spans diverse topics, with presentations comprising 4--28 slides and lasting 2--14~min, providing a valuable benchmark for the automatic generation and evaluation of academic presentation videos.}
\label{fig:stat}
\end{figure}
% (\kevin{long-horizon tasks, require multi-turn xxx, thus spend longer time, cost rather than natural vid.})
% video avg len
% slide number
% Despite 101, we emphasis agentic task rather simple video gen;
% [add figure]
\vspace{-0.5\baselineskip}
\subsection{Evaluation Metrics}
\vspace{-0.5\baselineskip}
Unlike natural video generation, academic presentation videos serve a highly specialized role: they are not merely about visual fidelity but about communicating scholarship. This makes it difficult to directly apply conventional metrics from video synthesis (\textit{e.g.}, FVD, IS, or CLIP-based similarity). Instead, their value lies in how well they \textit{disseminate research, amplify scholarly visibility.}
% \kevin{compress}
\vspace{-0.2\baselineskip}
From this perspective, we argue that a high-quality academic presentation video should be judged along two complementary dimensions (see Figure~\ref{fig:eval}):
\textbf{For the audience:}
the video is expected to faithfully convey the paper’s core ideas(\ie~motivation and contributions), while remaining accessible to audiences.
%the video must faithfully convey the paper’s central ideas, such as its motivation, problem formulation, and key contributions; and it should present these ideas in a manner that is easy to follow, allowing viewers from diverse backgrounds to understand the work without being overwhelmed.
\textbf{For the author:} the video should foreground the authors’ intellectual contribution and identity, and enhance the work’s visibility and impact.
To systematically capture these goals, we introduce tailored evaluation metrics specifically designed for academic presentation videos.
% why we need a pre; what define a good pre;
\vspace{-0.2\baselineskip}
\noindent\textbf{Meta Similarity} \textit{-- How video like human-made?}
%\kevin{As we have the ground-truth human-made demonstration videos,}
As we have the ground-truth human-made presentation videos with original slides, we evaluate how well the generated intermediate assets (\ie~speech, slides, and subtitles) aligned with the ones created by authors, which serves as the pseudo ground-truth.
(i) For each slide, we pair the slide image with its corresponding subtitles and submit both the generated pair and the human-made pair to the VLMs to obtain a similarity score on a five-point scale.
(ii) To further assess speech(\ie~vocal timbre), we uniformly sample a ten-second segment from the presentation audio, encode the generated and human-recorded audio with a speaking embedding model~\cite{audio_embedding}, and compute the cosine similarity between the embeddings to measure speech similarity.
\vspace{-0.2\baselineskip}
\noindent\textbf{PresentArena} \textit{-- Which video is better?} Similar to the human audience watching the presentation, we employ the VideoLLMs as the proxy audience to conduct pairwise comparisons of presentation videos, where the winning rate serves as the metric. For each pair, the model is queried twice in opposite orders: $(A,B)$ and $(B,A)$. This procedure reduces hallucinations and position bias. The two judgments are then aggregated by averaging to obtain a more stable preference estimation.
\vspace{-0.2\baselineskip}
\noindent\textbf{PresentQuiz} \textit{-- How videos conveys the paper knowledge?} Following prior work \cite{pang2025paper2poster}, we evaluate information coverage using a multiple-choice quiz on the presentation video. We first generate a set of questions with four options and the corresponding correct answers from the source paper. Then we ask the VideoLLMs to watch the presentation and answer each question. Overall accuracy serves as the metric, with higher accuracy indicating better information coverage.
% However, since generated video durations vary and longer videos can trivially include more content, we introduce a length penalty to overlong generations.
% In practice, consider that researchers usually intend to use concrete video to present the content thus we define a penalized weight $\alpha$ and aim to penalize the generated videos with too long duration: \begingroup
% \small % 可换成 \footnotesize 或 \scriptsize 更小
% % \begin{equation}
% $
% \alpha = \exp\!\left(-\,\frac{\max\{0,\,L^{\mathrm{gen}}-L^{\mathrm{gt}}\}}{L^{\mathrm{gt}}}\right), \tilde{\mathbf{s}} = \mathbf{s}\cdot \alpha,
% $
% % \end{equation}
% % \begin{equation}
% % \tilde{\mathbf{s}} = \mathbf{s}\cdot \alpha.
% % \end{equation}
% \endgroup
% where the $L^{\mathrm{gt}}$ and $L^{\mathrm{gen}}$ denote the ground-truth and generated video durations, and let $s$ be the original accuracy score.
% The penalized score, $\tilde{s}$, implies that a good presentation video should try to convey paper's information within limited duration.
\vspace{-0.3\baselineskip}
\noindent\textbf{IP Memory} \textit{-- How videos affect the author's visibility and work impact?} Another key purpose of academic presentation videos is to enhance the visibility and impact of the author’s work. Yet, this metric is unclear and difficult to simulate and thus remains an open problem. In real-conference settings, audiences who recall a scholar after attending their presentation are more inclined to pose relevant questions in later interactions. Motivated by this phenomenon, we propose a metric to assess how effectively a presentation video enables the audience to recall the work. Additional implementation details are provided in Appendix~\ref{sec:ip}.
\vspace{-0.3\baselineskip}
\noindent Furthermore, to ablate the contribution of each component, we evaluate both the quality and the gains provided by individual components (\eg~slides, cursor, and presenter). Notably, to further assess presentation videos from the user perspective, we conduct human studies to evaluate the results.
\begin{figure}[t]
\centering
\includegraphics[width=1\linewidth]{figure/eval.pdf}
\caption{\textbf{Overview of evaluation metrics.} We propose three metrics that systematically evaluate academic presentation video generation from the perspective of the relationship between the generated video and \textbf{(i)} the original paper and \textbf{(ii)} the human-made video.}
\label{fig:eval}
\vspace{-0.2\baselineskip}
\end{figure}
% \kevin{Furthermore, to ablate XXX, we devise a X (talking head), Y (cursor), Z (slide) to study gain by individual component, in appendix. Notably, we also include the human studies}
% the information coverage rate of the generated presentation video in respect to the original presentation video length.
% \noindent\textbf{Test-of-Memory.} \textit{-- How video influence its academic impact?} Inspired by live conference settings, this metric tests whether viewers can recall a work and formulate an appropriate question after watching the presentation, thereby assessing memorability and academic impact. For each method, we randomly sample four generated presentation videos and extract a ten-second clip from each. For every clip, we draw one question from \textit{PresentQuiz} associated with the corresponding paper. We then prompt a VideoLLM to watch the four clips. Next, we querry the model with an author portrait randomly sampled from the same set and ask it to select the question that best matches that author’s work. Overall accuracy is reported as the metric, with higher values indicating stronger memorability and question-elicitation ability.
% to systematically xxx, we devise the following metrics:
% (i) (Human-like) Similarity: how human-like with ground-truth video, how model prediction, but not a prefect; video, slides+subtitle, speech
% (ii) PresentArena: which one is better
% (iii) PresentQuiz: Motivated by the purpose of presentation, a good presentation should XXX, thus we design a
% (iv) Present-IP: identifier, academic IP
% [add figure--iii/iv]
```
## /assets/demo/latex_proj/section/checklist.tex
```tex path="/assets/demo/latex_proj/section/checklist.tex"
\section*{NeurIPS Paper Checklist}
%%% BEGIN INSTRUCTIONS %%%
The checklist is designed to encourage best practices for responsible machine learning research, addressing issues of reproducibility, transparency, research ethics, and societal impact. Do not remove the checklist: {\bf The papers not including the checklist will be desk rejected.} The checklist should follow the references and follow the (optional) supplemental material. The checklist does NOT count towards the page
limit.
Please read the checklist guidelines carefully for information on how to answer these questions. For each question in the checklist:
\begin{itemize}
\item You should answer \answerYes{}, \answerNo{}, or \answerNA{}.
\item \answerNA{} means either that the question is Not Applicable for that particular paper or the relevant information is Not Available.
\item Please provide a short (1–2 sentence) justification right after your answer (even for NA).
% \item {\bf The papers not including the checklist will be desk rejected.}
\end{itemize}
{\bf The checklist answers are an integral part of your paper submission.} They are visible to the reviewers, area chairs, senior area chairs, and ethics reviewers. You will be asked to also include it (after eventual revisions) with the final version of your paper, and its final version will be published with the paper.
The reviewers of your paper will be asked to use the checklist as one of the factors in their evaluation. While "\answerYes{}" is generally preferable to "\answerNo{}", it is perfectly acceptable to answer "\answerNo{}" provided a proper justification is given (e.g., "error bars are not reported because it would be too computationally expensive" or "we were unable to find the license for the dataset we used"). In general, answering "\answerNo{}" or "\answerNA{}" is not grounds for rejection. While the questions are phrased in a binary way, we acknowledge that the true answer is often more nuanced, so please just use your best judgment and write a justification to elaborate. All supporting evidence can appear either in the main paper or the supplemental material, provided in appendix. If you answer \answerYes{} to a question, in the justification please point to the section(s) where related material for the question can be found.
IMPORTANT, please:
\begin{itemize}
\item {\bf Delete this instruction block, but keep the section heading ``NeurIPS Paper Checklist"},
\item {\bf Keep the checklist subsection headings, questions/answers and guidelines below.}
\item {\bf Do not modify the questions and only use the provided macros for your answers}.
\end{itemize}
%%% END INSTRUCTIONS %%%
\begin{enumerate}
\item {\bf Claims}
\item[] Question: Do the main claims made in the abstract and introduction accurately reflect the paper's contributions and scope?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the abstract and introduction do not include the claims made in the paper.
\item The abstract and/or introduction should clearly state the claims made, including the contributions made in the paper and important assumptions and limitations. A No or NA answer to this question will not be perceived well by the reviewers.
\item The claims made should match theoretical and experimental results, and reflect how much the results can be expected to generalize to other settings.
\item It is fine to include aspirational goals as motivation as long as it is clear that these goals are not attained by the paper.
\end{itemize}
\item {\bf Limitations}
\item[] Question: Does the paper discuss the limitations of the work performed by the authors?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper has no limitation while the answer No means that the paper has limitations, but those are not discussed in the paper.
\item The authors are encouraged to create a separate "Limitations" section in their paper.
\item The paper should point out any strong assumptions and how robust the results are to violations of these assumptions (e.g., independence assumptions, noiseless settings, model well-specification, asymptotic approximations only holding locally). The authors should reflect on how these assumptions might be violated in practice and what the implications would be.
\item The authors should reflect on the scope of the claims made, e.g., if the approach was only tested on a few datasets or with a few runs. In general, empirical results often depend on implicit assumptions, which should be articulated.
\item The authors should reflect on the factors that influence the performance of the approach. For example, a facial recognition algorithm may perform poorly when image resolution is low or images are taken in low lighting. Or a speech-to-text system might not be used reliably to provide closed captions for online lectures because it fails to handle technical jargon.
\item The authors should discuss the computational efficiency of the proposed algorithms and how they scale with dataset size.
\item If applicable, the authors should discuss possible limitations of their approach to address problems of privacy and fairness.
\item While the authors might fear that complete honesty about limitations might be used by reviewers as grounds for rejection, a worse outcome might be that reviewers discover limitations that aren't acknowledged in the paper. The authors should use their best judgment and recognize that individual actions in favor of transparency play an important role in developing norms that preserve the integrity of the community. Reviewers will be specifically instructed to not penalize honesty concerning limitations.
\end{itemize}
\item {\bf Theory assumptions and proofs}
\item[] Question: For each theoretical result, does the paper provide the full set of assumptions and a complete (and correct) proof?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not include theoretical results.
\item All the theorems, formulas, and proofs in the paper should be numbered and cross-referenced.
\item All assumptions should be clearly stated or referenced in the statement of any theorems.
\item The proofs can either appear in the main paper or the supplemental material, but if they appear in the supplemental material, the authors are encouraged to provide a short proof sketch to provide intuition.
\item Inversely, any informal proof provided in the core of the paper should be complemented by formal proofs provided in appendix or supplemental material.
\item Theorems and Lemmas that the proof relies upon should be properly referenced.
\end{itemize}
\item {\bf Experimental result reproducibility}
\item[] Question: Does the paper fully disclose all the information needed to reproduce the main experimental results of the paper to the extent that it affects the main claims and/or conclusions of the paper (regardless of whether the code and data are provided or not)?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not include experiments.
\item If the paper includes experiments, a No answer to this question will not be perceived well by the reviewers: Making the paper reproducible is important, regardless of whether the code and data are provided or not.
\item If the contribution is a dataset and/or model, the authors should describe the steps taken to make their results reproducible or verifiable.
\item Depending on the contribution, reproducibility can be accomplished in various ways. For example, if the contribution is a novel architecture, describing the architecture fully might suffice, or if the contribution is a specific model and empirical evaluation, it may be necessary to either make it possible for others to replicate the model with the same dataset, or provide access to the model. In general. releasing code and data is often one good way to accomplish this, but reproducibility can also be provided via detailed instructions for how to replicate the results, access to a hosted model (e.g., in the case of a large language model), releasing of a model checkpoint, or other means that are appropriate to the research performed.
\item While NeurIPS does not require releasing code, the conference does require all submissions to provide some reasonable avenue for reproducibility, which may depend on the nature of the contribution. For example
\begin{enumerate}
\item If the contribution is primarily a new algorithm, the paper should make it clear how to reproduce that algorithm.
\item If the contribution is primarily a new model architecture, the paper should describe the architecture clearly and fully.
\item If the contribution is a new model (e.g., a large language model), then there should either be a way to access this model for reproducing the results or a way to reproduce the model (e.g., with an open-source dataset or instructions for how to construct the dataset).
\item We recognize that reproducibility may be tricky in some cases, in which case authors are welcome to describe the particular way they provide for reproducibility. In the case of closed-source models, it may be that access to the model is limited in some way (e.g., to registered users), but it should be possible for other researchers to have some path to reproducing or verifying the results.
\end{enumerate}
\end{itemize}
\item {\bf Open access to data and code}
\item[] Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that paper does not include experiments requiring code.
\item Please see the NeurIPS code and data submission guidelines (\url{https://nips.cc/public/guides/CodeSubmissionPolicy}) for more details.
\item While we encourage the release of code and data, we understand that this might not be possible, so “No” is an acceptable answer. Papers cannot be rejected simply for not including code, unless this is central to the contribution (e.g., for a new open-source benchmark).
\item The instructions should contain the exact command and environment needed to run to reproduce the results. See the NeurIPS code and data submission guidelines (\url{https://nips.cc/public/guides/CodeSubmissionPolicy}) for more details.
\item The authors should provide instructions on data access and preparation, including how to access the raw data, preprocessed data, intermediate data, and generated data, etc.
\item The authors should provide scripts to reproduce all experimental results for the new proposed method and baselines. If only a subset of experiments are reproducible, they should state which ones are omitted from the script and why.
\item At submission time, to preserve anonymity, the authors should release anonymized versions (if applicable).
\item Providing as much information as possible in supplemental material (appended to the paper) is recommended, but including URLs to data and code is permitted.
\end{itemize}
\item {\bf Experimental setting/details}
\item[] Question: Does the paper specify all the training and test details (e.g., data splits, hyperparameters, how they were chosen, type of optimizer, etc.) necessary to understand the results?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not include experiments.
\item The experimental setting should be presented in the core of the paper to a level of detail that is necessary to appreciate the results and make sense of them.
\item The full details can be provided either with the code, in appendix, or as supplemental material.
\end{itemize}
\item {\bf Experiment statistical significance}
\item[] Question: Does the paper report error bars suitably and correctly defined or other appropriate information about the statistical significance of the experiments?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not include experiments.
\item The authors should answer "Yes" if the results are accompanied by error bars, confidence intervals, or statistical significance tests, at least for the experiments that support the main claims of the paper.
\item The factors of variability that the error bars are capturing should be clearly stated (for example, train/test split, initialization, random drawing of some parameter, or overall run with given experimental conditions).
\item The method for calculating the error bars should be explained (closed form formula, call to a library function, bootstrap, etc.)
\item The assumptions made should be given (e.g., Normally distributed errors).
\item It should be clear whether the error bar is the standard deviation or the standard error of the mean.
\item It is OK to report 1-sigma error bars, but one should state it. The authors should preferably report a 2-sigma error bar than state that they have a 96\% CI, if the hypothesis of Normality of errors is not verified.
\item For asymmetric distributions, the authors should be careful not to show in tables or figures symmetric error bars that would yield results that are out of range (e.g. negative error rates).
\item If error bars are reported in tables or plots, The authors should explain in the text how they were calculated and reference the corresponding figures or tables in the text.
\end{itemize}
\item {\bf Experiments compute resources}
\item[] Question: For each experiment, does the paper provide sufficient information on the computer resources (type of compute workers, memory, time of execution) needed to reproduce the experiments?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not include experiments.
\item The paper should indicate the type of compute workers CPU or GPU, internal cluster, or cloud provider, including relevant memory and storage.
\item The paper should provide the amount of compute required for each of the individual experimental runs as well as estimate the total compute.
\item The paper should disclose whether the full research project required more compute than the experiments reported in the paper (e.g., preliminary or failed experiments that didn't make it into the paper).
\end{itemize}
\item {\bf Code of ethics}
\item[] Question: Does the research conducted in the paper conform, in every respect, with the NeurIPS Code of Ethics \url{https://neurips.cc/public/EthicsGuidelines}?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the authors have not reviewed the NeurIPS Code of Ethics.
\item If the authors answer No, they should explain the special circumstances that require a deviation from the Code of Ethics.
\item The authors should make sure to preserve anonymity (e.g., if there is a special consideration due to laws or regulations in their jurisdiction).
\end{itemize}
\item {\bf Broader impacts}
\item[] Question: Does the paper discuss both potential positive societal impacts and negative societal impacts of the work performed?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that there is no societal impact of the work performed.
\item If the authors answer NA or No, they should explain why their work has no societal impact or why the paper does not address societal impact.
\item Examples of negative societal impacts include potential malicious or unintended uses (e.g., disinformation, generating fake profiles, surveillance), fairness considerations (e.g., deployment of technologies that could make decisions that unfairly impact specific groups), privacy considerations, and security considerations.
\item The conference expects that many papers will be foundational research and not tied to particular applications, let alone deployments. However, if there is a direct path to any negative applications, the authors should point it out. For example, it is legitimate to point out that an improvement in the quality of generative models could be used to generate deepfakes for disinformation. On the other hand, it is not needed to point out that a generic algorithm for optimizing neural networks could enable people to train models that generate Deepfakes faster.
\item The authors should consider possible harms that could arise when the technology is being used as intended and functioning correctly, harms that could arise when the technology is being used as intended but gives incorrect results, and harms following from (intentional or unintentional) misuse of the technology.
\item If there are negative societal impacts, the authors could also discuss possible mitigation strategies (e.g., gated release of models, providing defenses in addition to attacks, mechanisms for monitoring misuse, mechanisms to monitor how a system learns from feedback over time, improving the efficiency and accessibility of ML).
\end{itemize}
\item {\bf Safeguards}
\item[] Question: Does the paper describe safeguards that have been put in place for responsible release of data or models that have a high risk for misuse (e.g., pretrained language models, image generators, or scraped datasets)?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper poses no such risks.
\item Released models that have a high risk for misuse or dual-use should be released with necessary safeguards to allow for controlled use of the model, for example by requiring that users adhere to usage guidelines or restrictions to access the model or implementing safety filters.
\item Datasets that have been scraped from the Internet could pose safety risks. The authors should describe how they avoided releasing unsafe images.
\item We recognize that providing effective safeguards is challenging, and many papers do not require this, but we encourage authors to take this into account and make a best faith effort.
\end{itemize}
\item {\bf Licenses for existing assets}
\item[] Question: Are the creators or original owners of assets (e.g., code, data, models), used in the paper, properly credited and are the license and terms of use explicitly mentioned and properly respected?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not use existing assets.
\item The authors should cite the original paper that produced the code package or dataset.
\item The authors should state which version of the asset is used and, if possible, include a URL.
\item The name of the license (e.g., CC-BY 4.0) should be included for each asset.
\item For scraped data from a particular source (e.g., website), the copyright and terms of service of that source should be provided.
\item If assets are released, the license, copyright information, and terms of use in the package should be provided. For popular datasets, \url{paperswithcode.com/datasets} has curated licenses for some datasets. Their licensing guide can help determine the license of a dataset.
\item For existing datasets that are re-packaged, both the original license and the license of the derived asset (if it has changed) should be provided.
\item If this information is not available online, the authors are encouraged to reach out to the asset's creators.
\end{itemize}
\item {\bf New assets}
\item[] Question: Are new assets introduced in the paper well documented and is the documentation provided alongside the assets?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not release new assets.
\item Researchers should communicate the details of the dataset/code/model as part of their submissions via structured templates. This includes details about training, license, limitations, etc.
\item The paper should discuss whether and how consent was obtained from people whose asset is used.
\item At submission time, remember to anonymize your assets (if applicable). You can either create an anonymized URL or include an anonymized zip file.
\end{itemize}
\item {\bf Crowdsourcing and research with human subjects}
\item[] Question: For crowdsourcing experiments and research with human subjects, does the paper include the full text of instructions given to participants and screenshots, if applicable, as well as details about compensation (if any)?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.
\item Including this information in the supplemental material is fine, but if the main contribution of the paper involves human subjects, then as much detail as possible should be included in the main paper.
\item According to the NeurIPS Code of Ethics, workers involved in data collection, curation, or other labor should be paid at least the minimum wage in the country of the data collector.
\end{itemize}
\item {\bf Institutional review board (IRB) approvals or equivalent for research with human subjects}
\item[] Question: Does the paper describe potential risks incurred by study participants, whether such risks were disclosed to the subjects, and whether Institutional Review Board (IRB) approvals (or an equivalent approval/review based on the requirements of your country or institution) were obtained?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the paper does not involve crowdsourcing nor research with human subjects.
\item Depending on the country in which research is conducted, IRB approval (or equivalent) may be required for any human subjects research. If you obtained IRB approval, you should clearly state this in the paper.
\item We recognize that the procedures for this may vary significantly between institutions and locations, and we expect authors to adhere to the NeurIPS Code of Ethics and the guidelines for their institution.
\item For initial submissions, do not include any information that would break anonymity (if applicable), such as the institution conducting the review.
\end{itemize}
\item {\bf Declaration of LLM usage}
\item[] Question: Does the paper describe the usage of LLMs if it is an important, original, or non-standard component of the core methods in this research? Note that if the LLM is used only for writing, editing, or formatting purposes and does not impact the core methodology, scientific rigorousness, or originality of the research, declaration is not required.
%this research?
\item[] Answer: \answerTODO{} % Replace by \answerYes{}, \answerNo{}, or \answerNA{}.
\item[] Justification: \justificationTODO{}
\item[] Guidelines:
\begin{itemize}
\item The answer NA means that the core method development in this research does not involve LLMs as any important, original, or non-standard components.
\item Please refer to our LLM policy (\url{https://neurips.cc/Conferences/2025/LLM}) for what should or should not be described.
\end{itemize}
\end{enumerate}
```
## /assets/demo/latex_proj/section/conclusion.tex
```tex path="/assets/demo/latex_proj/section/conclusion.tex"
\vspace{-0.4\baselineskip}
\section{Conclusions}
\vspace{-0.4\baselineskip}
This work tackles the long-standing bottleneck of presentation video generation by agent automation.
With \bench, we provide the first comprehensive benchmark and well-designed metrics to rigorously evaluate presentation videos in terms of quality, knowledge coverage, and academic memorability.
Our proposed \agent~framework demonstrates that automated generation of ready-to-use academic presentation videos is both feasible and effective, producing outputs that closely approximate author-recorded presentations while significantly reducing production time by 6 times.
We hope our work advances AI for Research and supports scalable scholarly communication.
```
## /assets/demo/latex_proj/section/introduction.tex
```tex path="/assets/demo/latex_proj/section/introduction.tex"
% Introduction
% story line:
% multi-modal long-document conditioned video generation
% motivation:
% manually create video for research present is labor-intensive
% much demand for explanatory videos to amplify research impact
% challenge
% no benchmark and metric
% ?
% [teaser]
% 1. reflect present video (paper input + slide + sub + talking head + cursor)
% 2.
\vspace{-1\baselineskip}
\section{Introduction}
\vspace{-0.3\baselineskip}
% [impact background] improtance of academic presentation video creation, how larbor-intensive it is. --> automatic presentation video generation is improtant and practially usefull.
% [compared with existing method] agent for sub-task, natural video gen
% [what we did] benchmark, p2vagent, evalution
% ##[impact background] automatic presentation video is labor-intensive important for academic communication, but it is labor-intensive including slide creation, talking head per slide / recording, subtitling;
% average spend a hour to develop a 5-10mins.
% ##[compared with existing method] Despite there has some work for auto PPT, poster, coding but automatically presentation video generation being a promising direction and less exploration.
% compare with natural video gen, presentation video is unique because
% 1. sourced from long-context paper (interleaved, multi-page, professional), information compression;
% 2. it pair with multiple aligned channel / multi-tasks: slide creation , text2speech, subtitling, talking head, cursor. project-level
% 3. lack of evaluation and metric. what define a good presentation video, considering the knowledge conveying via visual format, audio-friendly;
% In this work, we focus on this problem, particualry, we address two core problems:
% 1. how to automatically create a presentation video from paper;
% for this
% Paper2Video
% A:
% B:
% 2. how to evaluate a presentation video.
% for this,
% PaperTalk-101
Academic presentation videos are widely used in research communication, serving as a crucial and effective means to bridge researchers, as many conferences require them as an essential material for submission. However, the manual creation of such a video is highly labor-intensive, requiring slide design, subtitle writing, per-slide recording, and careful editing, which on average may take several hours to produce a $2$ to $10$ minute video for a scientific paper. Despite some prior works on slide and poster generation~\cite{sun2021d2s,zheng2025pptagent,pang2025paper2poster} and other AI4Research tasks~\cite{ai4research,writing_ass,goldsack2022making,paper2code,paper2agent}, automatic academic presentation video generation is a superproblem of them, a practical yet more challenging direction.
% such as Veo3~\cite{deepmind2025veo3},
\vspace{-0.2\baselineskip}
Unlike natural video generation~\cite{sd_video,show_1,wan,deepmind2025veo3}, presentation video exhibits distinctive characteristics, including multi-sensory integration, multi-figure conditioning, and high text density, which highlight the limitations of current natural video generation models~\cite{ma2025controllable}. Specifically, academic presentation video generation faces several crucial challenges:
\textit{a.} It originates from long-context papers that contain dense text as well as multiple figures and tables;
\textit{b.} It requires the coordination of multiple aligned channels, including slide generation~\cite{zheng2025pptagent}, subtitling, text-to-speech~\cite{tts-f5}, cursor control, and talking head generation~\cite{fantasytalking,cui2024hallo2};
\textit{c.} It lacks well-defined evaluation metrics: what constitutes a good presentation video, particularly in terms of knowledge conveyance and audience accessibility. Even for the state-of-the-art end-to-end video–audio generation model Veo3~\cite{deepmind2025veo3}, notable limitations remain in video length, clarity of dense on-screen text, and multi-modal long-document condition.
In this work, we try to solve these two core problems as shown in Figure~\ref{fig:teaser}.
%{\textbf{(i)} What defines a good academic presentation video}, and {\textbf{(ii)} How to effectively automatically generate such a video from a research paper}.
\vspace{-0.2\baselineskip}
To enable comprehensive evaluation of academic presentation video generation, we present the \textbf{\bench} Benchmark, comprising $101$ paired research papers and author-recorded presentation videos from recent conferences, together with original slides and speaker identity metadata. Based on this benchmark, we develop a suite of metrics to comprehensively evaluate generation quality from multiple dimensions:
\textbf{(i)} Meta Similarity — We employ a VLM to evaluate the alignment of generated slides and subtitles with human-designed counterparts.
\textbf{(ii)} PresentArena — We use a VideoLLM as a proxy audience to perform double-order pairwise comparisons between generated and human-made videos.
Notably, the primary purpose of a presentation is to \textit{effectively convey the information contained in the paper}. To this end, we introduce \textbf{(iii) PresentQuiz}, which treats the VideoLLMs as the audience and requires them to answer paper-derived questions given the videos. Furthermore, another important purpose of presentation video is to \textit{enhance the visibility and impact of the author’s work}. Motivated by real-conference interactions, we introduce \textbf{(iv) IP Memory}, which measures how well an audience can associate authors and works after watching presentation videos.
% \textbf{(iii) Academic IP} — Inspired by real conference scenarios, this metric examines whether, after watching a video, researchers can recall the work and formulate relevant questions, thereby measuring how memorable and academically impactful the presentation video is.
\begin{figure}[!t] % h=here, t=top, b=bottom, p=单独浮动页，!=放宽限制
\vspace{-1\baselineskip}
\centering
\small
\captionsetup{skip=2pt}
\includegraphics[width=\linewidth]{figure/teaser.pdf}
\caption{{This work solves two core problems for academic presentations:} \textbf{Left:} \textit{how to create a presentation video from a paper?} {\agent} -- an agent integrates slide, subtitling, cursor grounding, speech synthesis, and talking-head video rendering. \textbf{Right:} \textit{how to evaluate a presentation video?} {\bench} -- a benchmark with well-designed metrics to evaluate presentation quality.}
\label{fig:teaser}
\vspace{-0.5\baselineskip}
\end{figure}
% \kevin{here, quite long, need to have (i) (ii) (iii) to structure the process;}
\vspace{-0.2\baselineskip}
To effectively generate ready-to-use academic presentation videos, we propose \textbf{\agent}, the first multi-agent framework that enables academic presentation video generation from research papers and speaker identity. It integrates subsequent key modules: \textbf{(i)} Slide Generation. Instead of adopting the commonly used format (\textit{e.g.}, pptx, XML) from a template slide as in ~\cite{zheng2025pptagent}, we employ LaTeX code for slide generation from sketch, given its formal suitability for academic use and higher efficiency. Specifically, we employ a state-of-the-art Coder to generate code and introduce an effective \textbf{focused debugging} strategy, which iteratively narrows the scope and resolves compilation errors using feedback that indicates the relevant rows.
%\kevin{effective \textbf{debugging} strategy}.
To address the insensitivity of LLMs to fine-grained numerical adjustments, we propose a novel method called \textbf{Tree Search Visual Choice}. This approach systematically explores parameter variations to generate multiple branches, which are then concatenated into a single figure. A VLM is then tasked with selecting the optimal branch, thereby effectively improving element layouts such as figure and font size.
\textbf{(ii)} Subtitling and Cursor Grounding. We generate subtitles and cursor prompts for each sentence based on the slides. Then we achieve cursor spatial-temporal alignment using \textbf{Computer-use grounding model}~\cite{lin2025showui, qin2025ui} models and WhisperX~\cite{bain2023whisperx} respectively. \textbf{(iii)} Speech Synthesis and Talking-head Rendering. We synthesize personalized speech via text-to-speech models~\cite{chen2024f5} and produce talking-head videos~\cite{cui2024hallo2,fantasytalking} for author presentations. Inspired by human recording practice and the independence between each slide, we \textbf{parallelize generation} across slides, achieving a speedup of more than $\mathbf{6\times}$.
% \kevin{comment camel} Our multi-agent framework is implemented within the \texttt{CAMEL}\footnote{https://github.com/camel-ai/camel}, promoting simplicity and enabling scalability.
We will open-source all our data and codebase to empower the research community.
\vspace{-0.4\baselineskip}
To summarize, our contributions are as follows:
\vspace{-0.6\baselineskip}
\begin{itemize}[leftmargin=*]
\item We present \bench, the first high-quality benchmark of $101$ papers with author-recorded presentation videos, slides, and speaker metadata, together with evaluation metrics: Meta Similarity, PresentArena, PresentQuiz, and IP Memory.
\vspace{-0.2\baselineskip}
\item We propose {\agent}, the first multi-agent framework for academic presentation video generation. It introduces three key modules: \textbf{(i)} tree search visual choice for fine-grained slide generation; \textbf{(ii)} a GUI-grounding model coupled with WhisperX for spatial-temporal aligned cursor grounding; and \textbf{(iii)} slide-wise parallel generation to improve efficiency.
% \kevin{include a/b/c/d}, key insights such as visual mcts; leverage cua / whisperx for spatial-temporal-grounded alignment; to speedup, parallel
% the first multi-agent framework for academic presentation video generation, featuring unified multi-channel integration, CoT-based slide debugging with visual inspection, and parallel video synthesis for efficiency.
\vspace{-0.2\baselineskip}
\item Results on {\bench} confirm the effectiveness of {\agent}, which outperforms human-made presentations by 10\% in PresentQuiz accuracy and achieves comparable ratings in user studies, indicating that its quality approaches that of human-created content.
% which achieves \textbf{more than 10\% higher} PresentArena score, PresentQuiz accuracy, and IP Memory than top-performing baselines such as Veo3. [comparable with human-made]
% PresentArena score & human study - [comparable with human-made]
% \kevin{add details number regarding our optimization and improvement here\kevin{sota video-audio gen like veo3 demonstrate significant limitation (xx\%). meanwhile, our agent beat veo3, how sim. to human, other multi-agent }}
\end{itemize}
% to summary, our contributions are:
% 1. Benchmark
% % 1
% 2. For effective, agent core design -- module A: debug from code, enable it effectively debugging with visual inspection
% 3. For effecient, we design a parallel generation -- module B, which speedup the heavy talking head generation with \%x,
% % 2
% 2. we propose Paper2Video agent, it is the first multi-agent workflow, which integrate XXX tools work together, enable automatically without human;
% 3. To enhance coding-rich visual task, we develop a better debugging strategy,
% 4. Expes demonstratate, metric,
```
The content has been capped at 50000 tokens. The user could consider applying other filters to refine the result. The better and more specific the context, the better the LLM can follow instructions. If the context seems verbose, the user can refine the filter using uithub. Thank you for using https://uithub.com - Perfect LLM context for any GitHub repo.