Streaming Video Generation

Overview

Streaming video generation studies how to produce video a frame or chunk at a time so users can interact with it before the full sequence is complete. Most approaches adapt diffusion transformers to causal autoregressive generation, then use few-step distillation and self-forcing to reduce latency; rolling key-value caches and learned memory help retain useful context. Applications include interactive world models, talking avatars, and live video editing, with quality evaluated on measures such as VBench and long-horizon consistency benchmarks. The central tension is balancing real-time responsiveness and bounded memory with visual fidelity, motion quality, and coherence over long sequences, since causal generation can lose information available to slower bidirectional models.

Latest papers

CardsList

106 papers11 papers in the last four weeks, down 35% on the four weeks before. 0.1% of all new papers.

  1. Code World Model 2.0: Towards Infinite Controllable Video Generation

    Nov 17, 2026Ruoyu Wang, Hao Zhong, Yanming Yang +8Controllable Video GenerationReal-Time Interactive Video Generation

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

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

  3. Few-Step Streaming Video Generation via Condition Shifting

    Nov 10, 2026Deyuan Liu, Jungang Li, Kaiwen Zheng +8Streaming Video GenerationDistribution Matching Distillation

  4. TaoMate-HD: Progressive-Resolution Autoregressive Audio-Video Generation

    Nov 2, 2026Qijun Gan, Chenwei Zhang, Xinyang Li +3Audio-Video GenerationStreaming Video Generation

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

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

  6. ReferStream: Interactive Subject Injection for Streaming Video Generation

    Oct 27, 2026Shuolin Xu, Guanyuan Li, Boyu Li +5Subject-Driven Video GenerationStreaming Video Generation

  7. Attn-Forcing: Learning Full-Context Attention Proxies for Streaming Video Generation

    Oct 21, 2026Junyao Gao, Sibo Liu, Jiaxing Li +5Streaming Video GenerationMemory-Augmented Video Generation

  8. SolarRenderer: Few-Step Generative Reference Rendering

    Oct 20, 2026Guian Fang, Shengju Qian, Dongyue Lu +6Controllable Video GenerationVideo Diffusion Models

  9. TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video Generation

    Oct 19, 2026Jia Li, Xurui Peng, Haowei Zhu +7Autoregressive Video GenerationReal-Time Interactive Video Generation

  10. Speculative Forcing for Efficient Autoregressive Video Generation

    Oct 15, 2026Hyunwook Choi, Seungryong Kim, Dongyoon Han +1Efficient Video GenerationAutoregressive Video Generation

  11. Speculative Sampling in Interactive Video Generation

    Oct 14, 2026Yubo Huang, Yuxuan Zhang, Jiaming Liu +2Real-Time Interactive Video GenerationStreaming Video Generation

  12. StreamErase: Towards Ultra-Fast Streaming Video Erasing

    Oct 14, 2026Zhuobai Dong, Xiaobing Tu, Xiantao Zhang +4Video EditingStreaming Video Generation

  13. Connected Self Forcing: Beyond Local Learning in Video Autoregression

    Oct 8, 2026Dongbin Zhang, Chaoda Zheng, Kangjie Chen +13Autoregressive Video GenerationStreaming Video Generation

  14. Memory Forcing: Attendable Mid-Horizon History for Streaming Video Generation

    Oct 8, 2026Jiaming Zhang, Xinyu Wang, Huafeng Shi +2Streaming Video GenerationMemory-Augmented Video Generation

  15. SPW-Nav: A Streaming Panoramic World Model for Language-Guided Navigation

    Oct 6, 2026Yunheng Liu, Ziqi Cai, Siqi Yang +7Video GenerationVideo World Models

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

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

  17. Custom Forcing: Training-Free Subject Customization for Autoregressive Video Generation

    Oct 2, 2026Yunseung Ok, Hyunsoo Kim, Minseo Kim +1Identity-Preserving Video GenerationStreaming Video Generation

  18. No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation

    Sep 30, 2026Zejing Rao, Ketong Ren, Xiaoqiang Liu +3Streaming Video GenerationVideo Generation

  19. Self-Aligned Forcing: Streaming Video Diffusion with Differentiable Noisy History

    Sep 29, 2026Weiqiang Wang, Zhuokun Chen, Yusheng Dai +5Long-Horizon Video GenerationStreaming Video Generation

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

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

  21. Where and When to Force: Routed Forcing for Streaming Avatars

    Sep 25, 2026Zihan Su, Siwen Lu, Junhao Zhuang +6Streaming Video GenerationDiffusion Model Distillation