model · first seen 4 Oct 2026
autoregressive video diffusion
Also: AR-VDM, AR diffusion, AR video diffusion, causal video diffusion
Video generation models that produce frames sequentially with diffusion, conditioning on previously generated frames.
Mentions per week
PapersCodeDiscussion
Rank 153 on 16 Nov 2026 · 9 mentions in 28 days · 9 independent groups · papers → code · first seen 6 weeks ago · acceleration +1.21
Earliest sources
- PixReenact: Pixel-Conditioned Causal Video Diffusion for Streaming Head-Avatar ReenactmentPapers · 4 Oct 2026 · Gavriel Habib, Dvir Samuel, Or Shimshi, Rami Ben-Ari
- CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV CachesPapers · 7 Oct 2026 · Albert Ge, Akash Haridas, Utkarsh Saxena, Ruijing Yang, Ian Colbert, Frederic Sa…
- Conditional Residual Prediction: Improving Autoregressive Video Diffusion without a Bidirectional TeacherPapers · 8 Oct 2026 · Bowen Zheng, Zhiguang Liu, Jiarong Ou, Rui Chen, Tianyang Hu
- Memory Forcing: Attendable Mid-Horizon History for Streaming Video GenerationPapers · 8 Oct 2026 · Jiaming Zhang, Xinyu Wang, Huafeng Shi, Gangshan Wu, Limin Wang
- ForcingBooster: Adaptive Patch-wise Denoising for Fast Autoregressive Video DiffusionPapers · 8 Oct 2026 · Zekai Gu, Peng Wang, Jiahao Lu, Yongsen Mao, Cheng Lin, Yuan Liu
- IGL-HKUST/ForcingBoosterCode · 8 Oct 2026 · IGL-HKUST · 22 stars
Latest sources
- ScoutCache: Efficient Few-Step Autoregressive Video Diffusion via Conditional Readout and Selective CachingPapers · 16 Nov 2026 · Hao Tan, Jinghui Qin, Xuming Hu
- AR-Edit: Training-Free Autoregressive Video Editing without InversionPapers · 6 Nov 2026 · Hovhannes Margaryan, Quentin Bammey, Christian Sandor, Vicky Kalogeiton
- Trajectory Forcing: Exploiting Diffusion Trajectories for Autoregressive Long Video GenerationPapers · 6 Nov 2026 · Bohan Wang, Shuo Chen, Yunzhi Li, Zhaozheng Chen, Junzhe Zhang, Hanwang Zhang
- Training-Free Predictive Spatio-Temporal Token Pruning for Few-Step Autoregressive Video DiffusionPapers · 5 Nov 2026 · Jia Li, Xurui Peng, Xing Wang, Hayden Kwok-Hay So
- Runway Characters: Serving a 57B Video Diffusion Transformer for Real-Time ConversationPapers · 3 Nov 2026 · Rohan Agarwal, Robin Andeer, Alex Armbruster, Bennett Arthur, Michail Christos D…
- Disen-Forcing: Disentangling Semantic Anchoring from Motion for Autoregressive Video DiffusionPapers · 2 Nov 2026 · Zhengyang Yu, Akio Hayakawa, Masato Ishii, Qingtao Yu, Xuesong Li, Takashi Shibu…
- History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World ModelsPapers · 2 Nov 2026 · Hangyi Kuang, Chengzhi Wang, Yefei He, Weijie Wang, Yuke Zhao, Zhuokun Chen, Zis…
- ReelCache: An Efficient KV Cache Compression and Management System for Multi-Round Video GenerationPapers · 31 Oct 2026 · Tianyu Wang, Daiyang Yu, Zhiwei Ren, Junbo Li, Jitian Zhang, Longfei Shangguan
- Looking Ahead: Modeling Future Evolution in Autoregressive Video GenerationPapers · 21 Oct 2026 · Ruopeng Gao, Yukun Huang, Jiarui Hu, Shuai Wang, Wenbo Hu, Ying Shan, Limin Wang
- Dynamics-Aware Sparse Attention for Efficient Autoregressive Video DiffusionPapers · 19 Oct 2026 · Yuanyu He, Zhuokun Chen, Yefei He, Zhiwei Tang, Jiasheng Tang, Yinghao Yu, Jianf…
- TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video GenerationPapers · 19 Oct 2026 · Jia Li, Xurui Peng, Haowei Zhu, Tianyu Zhao, Jiexi Wang, Youwei Zheng, Yuxi Ren,…
- Clean Forcing: Drift-Resistant Autoregressive Video Diffusion with a Frozen BasePapers · 19 Oct 2026 · Wenqing Wang, Joonghyuk Shin, Jonathan Tremblay, Chan Hee Song, Yun Fu