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. K2V: Generative Keyframing For Physically Plausible Video Generation

    Nov 12, 2026Felix O'Mahony, Daniel Olmeda Reino, Roberto Cipolla +1Physical Consistency in Video GenerationVideo Diffusion Models

  2. TokenStream: Multi-Subject Personalized Video Generation with Token-wise LoRA and Guided Attention

    Nov 12, 2026Hung Nguyen, Quang Qui-Vinh Nguyen, Khoi NguyenIdentity-Preserving Video GenerationSubject-Driven Video Generation

  3. Selective Generative Restoration for Video Deraining via Uncertainty-Aware Diffusion

    Nov 12, 2026Yi'ang Chen, Han Li, Laibin Chang +3Video RestorationVideo Diffusion Models

  4. TRACE: Trajectory Synchronization for Training-Free Resolution Extension in Video Generation

    Nov 11, 2026Libo Zhu, Fan Li, Zhixin Wang +3High-Resolution Video GenerationVideo Diffusion Models

  5. Track4D: Representing Dense 3D Tracking for Video Diffusion Models

    Nov 11, 2026Yushi Lan, Zeren Jiang, Kelvin Li +33D Point TrackingVideo Diffusion Models

  6. Reframing Video Inverse Tone Mapping as Blind Posterior Inference via Latent Luminance Supervision

    Nov 11, 2026Hanwool Sul, Chang-Hoon Jeong, Kisung Shin +5HDR Video ReconstructionDiffusion-Based Inverse Problems

  7. When to Start Denoising? Adaptive Denoising Entry for Generative Video Compression

    Nov 10, 2026Zifu Zhang, Yuqiao Li, Ding Ding +5Generative Video CompressionNeural Video Compression

  8. Dark Matters: VAE-Aware HDR Encoding for SDR-to-HDR Video Reconstruction

    Nov 10, 2026Donghoon Cha, Bomseok Park, Hansl von Kwon +2HDR Video ReconstructionEquivariant Representation Learning

  9. MPEG-Diffusion: Mixed-Resolution Video Generation

    Nov 9, 2026Dennis Menn, Tianpei Gu, Guande He +7Video Diffusion ModelsEfficient Video Generation

  10. AR-Edit: Training-Free Autoregressive Video Editing without Inversion

    Nov 6, 2026Hovhannes Margaryan, Quentin Bammey, Christian Sandor +1Diffusion-Based Video EditingVideo Diffusion Models

  11. MotionCore: A Latent Neural Simulator for Video Generation with Rigid-Body Dynamics

    Nov 6, 2026Zheng Wang, Zhengwei Gong, Yuanzhi Liang +2Physical Consistency in Video GenerationTrajectory-Guided Video Generation

  12. InstaGen: Group-Shared Importance Sampling for Fast Video Generation

    Nov 5, 2026Kislay Aditya Oj, Kumar Krishna Agrawal, Sri Surya Varma Datla +1Efficient Video GenerationVideo Diffusion Models

  13. Householder Motion Embedding: Noise Modulation for Motion-Controllable Video Generation

    Nov 5, 2026Tao Jun Lin, Jinhong Ni, Ruyi Zha +4Controllable Video GenerationVideo Diffusion Models

  14. VA-TDM: A Unified View for Improving Few-Step Diffusion Models by Velocity Adversarial Distillation

    Nov 4, 2026Yihong Luo, Tianyu Pang, Tianyang HuDiffusion Model DistillationFew-Step Diffusion Sampling

  15. DecoupAttn: Decoupled Sparse Attention for Training-Free Acceleration of Video Diffusion

    Nov 4, 2026Yanjin Li, Bingbing Qiu, Qiang Huang +5Diffusion Model Inference AccelerationSparse Attention

  16. DualCast: Dual-Image Conditioned Diffusion Transformers for Digital Human E-Commerce Video Generation

    Nov 4, 2026Lifan Jiang, Yibo Zhao, Senlin Cheng +6Video GenerationImage-to-Video Generation

  17. FloMo: 3D Scene Flow as a World Action Model Intermediate for Learning from Human Video

    Nov 3, 2026Jeremy Collins, Namra Patel, Ayush Agarwal +2Robot Learning from VideoWorld Models for VLAs

  18. ReXMo: End-to-End Video Character Replacement with Expression and Motion Preservation

    Nov 3, 2026Hualiang Wei, Wenhui LiVideo Diffusion ModelsDiffusion-Based Video Editing

  19. HIVE-Diff: High Frame Rate HDR Video Reconstruction from a Single LDR Frame and Events

    Nov 2, 2026Caixin Wang, Qingrui Wang, Jie Zhang +1HDR Video ReconstructionEvent-Based Vision

  20. VidDub: Replacement-Aware Supervision for Two-Step Video Dubbing

    Nov 2, 2026Yexin Liu, Yunlong Lin, Zehan Wang +11Video Diffusion ModelsDiffusion-Based Video Editing

  21. Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video Diffusion

    Nov 2, 2026Zhengyang Yu, Akio Hayakawa, Masato Ishii +5Video Diffusion ModelsAutoregressive Video Generation

  22. Recoverability-Aware Evaluation of Diffusion Video Inpainting and Object Removal

    Nov 1, 2026Yanliang Qi, Jiacheng Ding, Cong Guo +1Video EditingDiffusion-Based Video Editing

  23. Wave Forcing: Towards Speed-of-Light Streaming Video Generation

    Oct 31, 2026Yijie Jin, Yuxuan Liu, Jiajun Xu +7Streaming Video GenerationLong Video Generation