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. When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models

    Feb 21, 2026Zhixiang Guo, Siyuan Liang, Andras Balogh +4Adversarial Attacks on World ModelsAdversarial Attacks

  2. Predict to Skip: Linear Multistep Feature Forecasting for Efficient Diffusion Transformers

    Feb 20, 2026Hanshuai Cui, Zhiqing Tang, Qianli Ma +3Diffusion Model AccelerationDiffusion Sampling

  3. Unified Latents (UL): How to train your latents

    Feb 19, 2026Jonathan Heek, Emiel Hoogeboom, Thomas Mensink +1Diffusion AutoencoderLatent Diffusion Models

  4. CHAI: CacHe Attention Inference for text2video

    Feb 18, 2026Joel Mathew Cherian, Ashutosh Muralidhara Bharadwaj, Vima Gupta +1T2V GenerationEfficient Video Generation

  5. VideoSketcher: Sequential Sketch Generation Using Video Model Priors

    Feb 17, 2026Hui Ren, Yuval Alaluf, Omer Bar Tal +3Video Diffusion Models

  6. World Action Models are Zero-shot Policies

    Feb 17, 2026Seonghyeon Ye, Yunhao Ge, Kaiyuan Zheng +33World Action ModelsZero-Shot Robotic Manipulation

  7. PISCO: Precise Video Instance Insertion with Sparse Control

    Feb 9, 2026Xiangbo Gao, Renjie Li, Xinghao Chen +4Physical Consistency in Video GenerationVideo Diffusion Models

  8. FlashBlock: Attention Caching for Efficient Long-Context Block Diffusion

    Feb 5, 2026Zhuokun Chen, Jianfei Cai, Bohan ZhuangVideo Diffusion ModelsSelf-Attention

  9. PISA: Piecewise Sparse Attention Is Wiser for Efficient Diffusion Transformers

    Feb 1, 2026Haopeng Li, Shitong Shao, Wenliang Zhong +4Diffusion Model Inference AccelerationAttention Approximation

  10. VMonarch: Efficient Video Diffusion Transformers with Structured Attention

    Jan 29, 2026Cheng Liang, Haoxian Chen, Liang Hou +4Video Diffusion ModelsDiffusion Transformer

  11. Zero-Shot Video Restoration and Enhancement with Assistance of Video Diffusion Models

    Jan 29, 2026Cong Cao, Huanjing Yue, Shangbin Xie +2Video RestorationTemporal Consistency in Video Restoration

  12. AnyView: Synthesizing Any Novel View in Dynamic Scenes

    Jan 23, 2026Basile Van Hoorick, Dian Chen, Shun Iwase +7Multi-View ConsistencyCamera-Conditioned Video Generation

  13. Beyond Inpainting: Unleash 3D Understanding for Stable Camera-Controlled Video Generation

    Jan 15, 2026Dong-Yu Chen, Yixin Guo, Shuojin Yang +2Camera-Controlled Video GenerationVideo Diffusion Models

  14. Mixture of Distributions Matters: Dynamic Sparse Attention for Efficient Video Diffusion Transformers

    Jan 14, 2026Yuxi Liu, Yipeng Hu, Zekun Zhang +2Video Diffusion ModelsDiffusion Transformer

  15. Diffusion-DRF: Free, Rich, and Differentiable Reward for Video Diffusion Fine-Tuning

    Jan 7, 2026Yifan Wang, Yanyu Li, Gordon Guocheng Qian +3Diffusion Model AlignmentDiffusion Model Fine-Tuning

  16. Slot-ID: Identity-Preserving Video Generation from Reference Videos via Slot-Based Temporal Identity Encoding

    Jan 4, 2026Yixuan Lai, He Wang, Kun Zhou +1Video Diffusion ModelsT2V Generation

  17. InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion

    Dec 19, 2025Hoiyeong Jin, Hyojin Jang, Junha Hyung +6Video Diffusion ModelsVideo Editing

  18. End-to-End Training for Autoregressive Video Diffusion via Self-Resampling

    Dec 17, 2025Yuwei Guo, Ceyuan Yang, Hao He +5Video Diffusion ModelsAutoregressive Diffusion

  19. Elastic3D: Controllable Stereo Video Conversion with Guided Latent Decoding

    Dec 16, 2025Nando Metzger, Prune Truong, Goutam Bhat +2Video Diffusion ModelsStereo Vision

  20. AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis

    Dec 12, 2025Junjie Ye, Rong Xue, Basile Van Hoorick +4Video Diffusion ModelsSynthetic Data Generation for Robotics

  21. GimbalDiffusion: Gravity-Aware Camera Control for Video Generation

    Dec 9, 2025Frédéric Fortier-Chouinard, Yannick Hold-Geoffroy, Valentin Deschaintre +2Camera-Controlled Video GenerationVideo Diffusion Models

  22. Single-step Diffusion-based Video Coding with Semantic-Temporal Guidance

    Dec 8, 2025Naifu Xue, Zhaoyang Jia, Jiahao Li +4Diffusion Model GuidanceVideo Diffusion Models