Overview

Video diffusion models synthesize or transform frame sequences by denoising video latents, often in diffusion transformers, conditioned on text, images, reference clips, or structured controls. Researchers use temporal attention, autoregressive chunking, and pose, camera, depth, or physics cues to improve motion, identity, geometry, and interaction; related systems support editing, restoration, avatars, and world-model prediction. Evaluation spans prompt alignment and visual quality, using benchmarks such as VBench and FVD, as well as controllability, physical plausibility, and downstream action performance. A central challenge is balancing fidelity and precise control over long videos with the speed and memory needed for streaming, while limiting drift and physically implausible events.

Latest papers

CardsList

812 papers72 papers in the last four weeks, down 36% on the four weeks before. 0.5% of all new papers.

  1. AURA: AUdio-dRiven streaming Avatar

    Nov 19, 2026Nathaniel Cohen, Nicolas Dufour, Amélie Royer +2Audio-Video GenerationReal-Time Interactive Video Generation

  2. ViDecide: Teaching Video Diffusion Models to Reason and Plan Step by Step

    Nov 19, 2026Kaiwen Zhang, Yiming Gao, Zeqi Xiao +4Video Diffusion ModelsVideo Generation

  3. Online Temporal Rotations for 2 Bit KV-Cache Quantization in Video Diffusion Transformers

    Nov 19, 2026Ryan Lucas, Petros Prastakos, Rahul MazumderKV-Cache QuantizationDiffusion Model Quantization

  4. FlexVSR: Continuous-Scale Super-Resolution for Streaming Video Generation

    Nov 19, 2026Ji Wang, Haonan An, Jiasheng Zhang +1Video Super-ResolutionStreaming Video Generation

  5. StreamEgo: Streaming Exocentric-to-Egocentric Video Generation

    Nov 19, 2026Tianyi Xu, Boyang Lyu, Yunkai Tang +6Exocentric-to-Egocentric Video GenerationStreaming Video Generation

  6. MultiBinder: Preventing Multi-Subject Identity Leakage in Personalized Video Generation

    Nov 19, 2026Wei Li, Yiheng Zhang, Zhaofan Qiu +3Identity-Preserving Video GenerationVideo Generation

  7. Frequency-Synchronized Boundary Coupling for Training-Free Multi-Prompt Long Video Generation

    Nov 19, 2026Yipan Xu, Shuyong Gao, Jiyuan Fu +5Video GenerationLong Video Generation

  8. ContextRenderer: Dynamic-Context Video Generation for Interactive Game Worlds

    Nov 19, 2026Runze Wang, Fei Zha, Bing He +7Video Diffusion ModelsReal-Time Interactive Video Generation

  9. H3Remover: Reinforcing Video Object Removal without Paired Data

    Nov 18, 2026Kangjie Chen, Xiangyu Li, Jinhao Deng +10Video EditingVideo Diffusion Models

  10. Every Query Routes Itself: Accelerating Video Diffusion Transformers with Per-Query Routed Sparse Attention

    Nov 18, 2026Zhen Huang, Shuwei Li, Ruizhe Yao +9Sparse AttentionDiffusion Model Inference Acceleration

  11. Spark-H3: Adaptive Block Sparse Attention for Video Diffusion Models

    Nov 18, 2026Zecheng Tang, Jiaye Fu, Youtian Lin +5Block-Sparse AttentionDiffusion Model Inference Acceleration

  12. Autoregressive View Model

    Nov 17, 2026Jensen, Zhou, Samuel Rota Bulo +8Camera-Controlled Video GenerationAutoregressive 3D Scene Generation

  13. FastFrames: Video Generation at Interactive Latency

    Nov 17, 2026Gene Chou, Guandao Yang, Fujun Luan +4Video Diffusion ModelsReal-Time Interactive Video Generation

  14. When a Larger Guidance Scale Repairs Text-to-Video Failures and When It Does Not

    Nov 17, 2026Taewon Kang, Matthias ZwickerT2V GenerationDiffusion Model Guidance

  15. Harnessing Image Diffusion Prior for Photo-Realistic Video Restoration

    Nov 17, 2026Fanghua Yu, Hongyu An, Jinfan Hu +6Video RestorationTemporal Consistency in Video Restoration

  16. Streaming Generative Video Compression with Embedding Alignment and In-Context Propagation

    Nov 17, 2026Zhitao Wang, Hengyu Man, Han Liu +3Generative Video CompressionNeural Video Compression

  17. Evolve in Panorama, Render in View: Panoramic World State Evolution for Video World Models

    Nov 17, 2026Longtao Jiang, Mingfei Han, Jianmin Bao +7World ModelsVideo World Models

  18. Decoding Without a Decoder: Direct Pixel Prediction from Diffusion Transformers

    Nov 17, 2026Hansheng Chen, Shengqu Cai, Jan Ackermann +4Diffusion ModelsDiffusion Transformer

  19. BATMoS: Budget-Aware Guidance Allocation for Efficient Video Diffusion

    Nov 17, 2026Zhixu Du, Kuo Yang, Jingwei Sun +2Video Diffusion ModelsDiffusion Model Guidance

  20. MovieRoll: A Systematic Framework for Rolling Out Long-Form Videos

    Nov 16, 2026Yunyang Ge, Weijie Kong, Ryan Xu +9Long-Horizon Video GenerationVideo Generation

  21. ScoutCache: Efficient Few-Step Autoregressive Video Diffusion via Conditional Readout and Selective Caching

    Nov 16, 2026Hao Tan, Jinghui Qin, Xuming HuDiffusion Model Inference AccelerationVideo Diffusion Models

  22. Restoring Diversity in Distilled Image and Video Generators by Probing Activations

    Nov 13, 2026Furkan Horoz, Ozgur Kara, Kaan Oktay +4Diffusion Model DistillationDiffusion-Based Image Generation

  23. JVT: Just Video Transformer makes pixel-space video diffusion simple

    Nov 13, 2026Jianjun Zhou, Hua Geng, Haoyu GuoVideo Diffusion ModelsPixel-Space Diffusion Models

  24. LongCat-Video-Avatar 1.6 Technical Report

    Nov 13, 2026Meituan LongCat Team, Xunliang Cai, Yiqi Chen +8Audio-Video GenerationAudio-Driven Facial Animation

  25. Back to Pixels: Lifting Latent Video Diffusion into Pixel Space

    Nov 12, 2026Yanke Song, Shuo Chen, Chris Rockwell +9Video Diffusion ModelsHigh-Resolution Video Generation