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. Diverse Motion Customization via Control-based Dynamic Optimization

    Oct 6, 2026Youngyoon Choi, Kihyun Kim, Jeongwoo Shin +1Video Diffusion ModelsControllable Video Generation

  2. S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation

    Oct 5, 2026Jeffrey Hu, Daniel Olmeda Reino, Ayush TewariPhysical Consistency in Video GenerationVideo Diffusion Models

  3. MC-Sparse: Deconstructing and Closing the Dense-Sparse Attention Gap in Diffusion Transformers

    Oct 5, 2026Jiarui Chen, Zeqiang Lai, Jiangshan Wang +5Video Diffusion ModelsDiffusion Transformer

  4. KineWorld: Action-Induced Transport Fields for Embodied World Modeling

    Oct 5, 2026Ziying Song, Yuchen Liu, Zhuoran Xu +6Action-Conditioned Video GenerationVideo Diffusion Models

  5. Level-of-Token Diffusion

    Oct 5, 2026Kiyohiro Nakayama, Brian Chao, Jan Ackermann +5Video Diffusion ModelsAdaptive Tokenization

  6. DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video Generation

    Oct 2, 2026Jiahao Zhan, Yan Wang, Yongrui Ma +5Single-Step Video GenerationStreaming Video Generation

  7. XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation

    Oct 2, 2026Tingting Du, Ziyao Wang, Guoheng Sun +1World Action ModelsRobotic Manipulation

  8. UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene Generation

    Oct 2, 2026Daikun Liu, Xin Zhan, Teng Wang +24D Scene GenerationVideo Prediction

  9. Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion Models

    Oct 2, 2026Jonas Kneifl, Jakub Skalski, Bartłomiej Twardowski +1Video Diffusion ModelsPhysical Reasoning in Video

  10. In-Distribution Forcing for Long Video Generation at Test Time

    Oct 2, 2026Jeongwoo Shin, Youngyoon Choi, Sangwoo Jo +5Long Video GenerationVideo Diffusion Models

  11. Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion Model

    Oct 2, 2026Yunjiao Zhou, Junlang Qian, Lihua Xie +1Human Motion GenerationText-to-Motion Generation

  12. Token-Level Video Reinforcement Learning

    Oct 1, 2026Yifan Wang, Gordon Guocheng Qian, Yanyu Li +2Video Diffusion ModelsRL for Video Generation

  13. Video Generation Models: A Survey of Post-Training and Alignment

    Sep 30, 2026Chaoyu Li, Xiaoyi Gu, Yogesh Kulkarni +10Video Diffusion ModelsControllable Video Generation

  14. FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video Unlearning

    Sep 30, 2026Łukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1Video Diffusion ModelsDiffusion Model Unlearning

  15. PartiCam: Camera Controlled Video Generation with Reward Guidance

    Sep 30, 2026Amine Ouasfi, Runjia Li, Junlin Han +3Diffusion Model GuidanceCamera-Controlled Video Generation

  16. TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment Conditioning

    Sep 30, 2026Zijing Qin, Jun Zhou, Ruicheng Zhang +5Virtual Try-OnVideo Diffusion Models

  17. Uncertainty-Aware Consistency Distillation for Few-Step Video Generation

    Sep 30, 2026Lingyu Liu, Yaxiong Wang, Li Zhu +1Video Diffusion ModelsFew-Step Diffusion Sampling

  18. PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion Transformers

    Sep 30, 2026Yun Dai, Jiarui Wen, Huiping Zhuang +2Video Diffusion ModelsDiffusion Transformer

  19. Future Video Generation Better Aligns with the Human Visual Cortex than Observed Video

    Sep 30, 2026Chang-Bae Bang, Hyungjin Chung, Byung-Hoon KimVideo Diffusion ModelsPredictive Coding

  20. EPIC: Epipolar-Consistent 360° Immersive Stereo Video Generation

    Sep 30, 2026Debabrata Mandal, Dongdong Fu, Jonathon Miller +3Video Diffusion Models

  21. Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE

    Sep 29, 2026Yu Xu, Yuxin Zhang, Xiao Yang +7Video Diffusion ModelsVideo Generation

  22. DIET: Deletion-response Expert Trimming for Video Diffusion Transformers

    Sep 29, 2026Jiachang Zhang, Teng Hu, Bohao Feng +4Mixture-of-Experts PruningVideo Diffusion Models

  23. Waypoint-1.5: A Real-Time Video World Model for Consumer Hardware

    Sep 29, 2026Rajit Rajpal, Shahbuland Matiana, Liew Wei Pyn +12Game World ModelsVideo Diffusion Models

  24. Salt++: Context-Aligned Post-Training for Few-Step Streaming Multimodal Generation

    Sep 29, 2026Xingtong Ge, Yutong Wang, Lunjie Zhu +7Streaming Video GenerationVideo Diffusion Models