# Paper2Video: Automatic Video Generation from Scientific Papers

arXiv: https://arxiv.org/abs/2510.05096 · HTML: https://mlsanity.com/paper/2510.05096/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 39 references that are in the map.
- First posted on arXiv 6 Oct 2025.

## Builds on (most cited first, 30 of 34)

- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [UI-TARS: Pioneering Automated GUI Interaction with Native Agents](https://mlsanity.com/paper/2501.12326/) (2025)
- [A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers](https://mlsanity.com/paper/2105.03011/) (2021)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [WhisperX: Time-Accurate Speech Transcription of Long-Form Audio](https://mlsanity.com/paper/2303.00747/) (2023)
- [PaperBench: Evaluating AI's Ability to Replicate AI Research](https://mlsanity.com/paper/2504.01848/) (2025)
- [Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation](https://mlsanity.com/paper/2309.15818/) (2023)
- [ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery](https://mlsanity.com/paper/2410.05080/) (2024)
- [ShowUI: One Vision-Language-Action Model for GUI Visual Agent](https://mlsanity.com/paper/2411.17465/) (2024)
- [Controllable Video Generation: A Survey](https://mlsanity.com/paper/2507.16869/) (2025)
- [Multi-XScience: A Large-scale Dataset for Extreme Multi-document Summarization of Scientific Articles](https://mlsanity.com/paper/2010.14235/) (2020)
- [Hallo2: Long-Duration and High-Resolution Audio-Driven Portrait Image Animation](https://mlsanity.com/paper/2410.07718/) (2024)
- [BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology](https://mlsanity.com/paper/2503.00096/) (2025)
- [Automated Movie Generation via Multi-Agent CoT Planning](https://mlsanity.com/paper/2503.07314/) (2025)
- [PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides](https://mlsanity.com/paper/2501.03936/) (2025)
- [MS2: Multi-Document Summarization of Medical Studies](https://mlsanity.com/paper/2104.06486/) (2021)
- [FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis](https://mlsanity.com/paper/2504.04842/) (2025)
- [IconShop: Text-Guided Vector Icon Synthesis with Autoregressive Transformers](https://mlsanity.com/paper/2304.14400/) (2023)
- [LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models](https://mlsanity.com/paper/2504.10415/) (2025)
- [Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning](https://mlsanity.com/paper/2504.17192/) (2025)
- [Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers](https://mlsanity.com/paper/2505.21497/) (2025)
- [AI4Research: A Survey of Artificial Intelligence for Scientific Research](https://mlsanity.com/paper/2507.01903/) (2025)
- [Open-Source Conversational AI with SpeechBrain 1.0](https://mlsanity.com/paper/2407.00463/) (2024)
- [Making Science Simple: Corpora for the Lay Summarisation of Scientific Literature](https://mlsanity.com/paper/2210.09932/) (2022)
- [D2S: Document-to-Slide Generation Via Query-Based Text Summarization](https://mlsanity.com/paper/2105.03664/) (2021)
- [SciReplicate-Bench: Benchmarking LLMs in Agent-driven Algorithmic Reproduction from Research Papers](https://mlsanity.com/paper/2504.00255/) (2025)
- [FlowVQTalker: High-Quality Emotional Talking Face Generation through Normalizing Flow and Quantization](https://mlsanity.com/paper/2403.06375/) (2024)
- [MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation](https://mlsanity.com/paper/2411.15262/) (2024)

## Built on by (most cited first, 24 of 24)

- [SlideTailor: Personalized Presentation Slide Generation for Scientific Papers](https://mlsanity.com/paper/2512.20292/) (2025)
- [DECKBench: Benchmarking Multi-Agent Frameworks for Academic Slide Generation and Editing](https://mlsanity.com/paper/2602.13318/) (2026)
- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design](https://mlsanity.com/paper/2608.13560/) (2026)
- [Human-Agent Collaborative Paper-to-Page Crafting](https://mlsanity.com/paper/2510.19600/) (2025)
- [Paper2SysArch: Structure-Constrained System Architecture Generation from Scientific Papers](https://mlsanity.com/paper/2511.18036/) (2025)
- [DIRECT: Video Mashup Creation via Hierarchical Multi-Agent Planning and Intent-Guided Editing](https://mlsanity.com/paper/2604.04875/) (2026)
- [CutClaw: Agentic Hours-Long Video Editing via Music Synchronization](https://mlsanity.com/paper/2603.29664/) (2026)
- [Benchmark Everything Everywhere All at Once](https://mlsanity.com/paper/2606.06462/) (2026)
- [IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection](https://mlsanity.com/paper/2603.29602/) (2026)
- [PresentAgent-2: Towards Generalist Multimodal Presentation Agents](https://mlsanity.com/paper/2605.11363/) (2026)
- [PaperX: A Unified Framework for Multimodal Academic Presentation Generation with Scholar DAG](https://mlsanity.com/paper/2602.03866/) (2026)
- [EvoDiagram: Agentic Editable Diagram Creation via Design Expertise Evolution](https://mlsanity.com/paper/2604.09568/) (2026)
- [ManimAgent: Self-Evolving Multimodal Agents for Visual Education](https://mlsanity.com/paper/2606.30296/) (2026)
- [ResearchStudio-Reel: Automate the Last Mile of Research from Paper to Poster, Video, and Blog](https://mlsanity.com/paper/2607.04438/) (2026)
- [TeachMaster: Generative Teaching via Code](https://mlsanity.com/paper/2601.04204/) (2025)
- [World Models as an Intermediary between Agents and the Real World](https://mlsanity.com/paper/2602.00785/) (2026)
- [Unifying Scientific Communication: Fine-Grained Correspondence Across Scientific Media](https://mlsanity.com/paper/2605.05831/) (2026)
- [A Survey on Foundations and Frontiers of Multimodal Agentic Frameworks: Techniques and Applications](https://mlsanity.com/paper/2608.20379/) (2026)
- [StreamWise: Serving Multi-Modal Generation in Real-Time at Scale](https://mlsanity.com/paper/2603.05800/) (2026)
- [Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures](https://mlsanity.com/paper/2606.12576/) (2026)
- [EduPanel: A Three-Agent LLM Judge for Teaching Videos -- Reliability, Complementarity, and Human Trust Calibration](https://mlsanity.com/paper/2607.18529/) (2026)
- [ConvDeck: Conversational Paper-to-Slide Generation via Stage-Specific User Feedback](https://mlsanity.com/paper/2609.00226/) (2026)
- [FigAct: Turning Scientific Figures into Active Canvases for Explanation](https://mlsanity.com/paper/2609.36190/) (2026)

## Abstract (arXiv)

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: 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 Paper2Video, 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, PresentQuiz, and IP Memory--to measure how videos convey the paper's information to the audience. Building on this foundation, we propose PaperTalker, the first multi-agent framework for academic presentation video generation. It integrates slide generation with effective layout refinement by a novel effective tree search visual choice, cursor grounding, subtitling, speech synthesis, and talking-head rendering, while parallelizing slide-wise generation for efficiency. Experiments on Paper2Video 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 dataset, agent, and code are available at https://github.com/showlab/Paper2Video.