Attn-Forcing is a new framework for streaming video generation that preserves full-context attention contributions while operating under bounded memory and computation. It introduces learnable visual latents as attention proxies, updated via a Proxy Update Module to incorporate historical visual context, and employs an Attention Matching Loss to explicitly supervise the proxies using full-context attention. Experiments show that Attn-Forcing consistently improves video generation quality and outperforms existing baseline methods.
By Junyao Gao, Sibo Liu, Jiaxing Li, Yanan Sun, Hanxin Zhu, Weidong Zhang, Jun Zhang, Cairong Zhao
Focused Forcing is a training‑free method for selecting key‑value (KV) cache entries in autoregressive video diffusion models. It selects historical frames per generated frame by combining attention and diversity scores, and allocates larger budgets to more important heads. The approach yields up to 1.48× faster generation while improving visual quality and text alignment across several generation paradigms.
By Peiliang Cai, Evelyn Zhang, Jiacheng Liu, Hao Lin, Ruiqi Zhang, Weile Mo, Yue Ma, Shikang Zheng, Jiehang Huang, Dongrui Liu, Linfeng Zhang
arXiv:2610.10429v1 Announce Type: new
Abstract: Autoregressive video generation requires denoising the current frames while writing their key-value representations as context for future predictions....
By Zihan Su, Junhao Zhuang, Yaowei Li, Siwen Lu, Haoran Li, Lingen Li, Haoyu Wu, Weiyang Jin, Songchun Zhang, Haoyang Huang, Chun Yuan, Zeyue Xue, Nan Duan
Recent advancements in MLLM-based long-form video understanding have mitigated inference-time computational cost and limited context lengths by selecting query-relevant frames. However, existing approaches predominantly rely on external proxy scorers and rigid heuristic rules, inevitably suffering from misalignment with the target MLLM's intrinsic evidence and failing to accommodate the non-uniform spatiotemporal information density.
arXiv:2602. 01801v2 Announce Type: replace-cross Abstract: Autoregressive video diffusion models enable streaming generation, opening the door to long-form synthesis, video world models, and interactive neural game engines.
By Dvir Samuel, Issar Tzachor, Matan Levy, Michael Green, Gal Chechik, Rami Ben-Ari
arXiv:2606. 16353v1 Announce Type: cross Abstract: Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.
By Haonan Ge, Yiwei Wang, Hang Wu, Yujun Cai
arXiv:2602. 05305v3 Announce Type: replace-cross Abstract: Generating long-form content, such as minute-long videos and extended texts, is increasingly important for modern generative models.
By Zhuokun Chen, Jianfei Cai, Bohan Zhuang
arXiv:2610.33589v1 Announce Type: new
Abstract: While interactive video world models require autoregressive generation, directly adapting pretrained bidirectional video diffusion models into autoregr...
By Zelin Gao, Hao Ouyang, Jiapeng Zhu, Qiuyu Wang, Jingye Chen, Zichen Liu, Xing Zhu, Yujun Shen, Yinghao Xu
arXiv:2609.00291v1 Announce Type: new
Abstract: Streaming video understanding requires answering questions that arrive at arbitrary moments over an unbounded video stream. Existing systems primarily...
By Ce Zhang, Jing Bi, Jinxi He, Jianshu Zhang, Jingyang Lin, Yunzhong Xiao, Minghao Fu, Yaqi Xie, Zhentao Xie, Weicong Chen, Katia Sycara, Ming Zhou
The paper introduces Prediction‑Aligned Context Compaction (PACC), a method that learns a compact memory representation for long‑video generation by distilling a frozen video generator. PACC trains a compressor to aggregate past frames into memory tokens, using the generator as both teacher and student during on‑policy distillation. Experiments on MBench and VBench‑Long show that PACC improves memory‑event coverage and consistency, achieving better scores than strong baselines and producing competitive minute‑long videos.
By Xiaoyu Wu, Weihang Guo, Yifei Wang, Xinze Feng, Lydia E. Kavraki, Zhiwei Steven Wu
The paper introduces MaLoW, a streaming memory framework that internalizes long‑term video history into evolving lightweight parameter updates using a recurrent HyperNetwork and LoRA weights. MaLoW keeps current observations as input while carrying historical context forward without re‑visiting the full video stream. The authors also present MaLoW‑Instruct, a large streaming video dataset, and show that MaLoW outperforms prior memory methods on several benchmarks and improves action success in a vision‑language‑action setting.
By Zhuoming Liu, Jinhong Lin, Lin Zhang, Yiwu Zhong, Yin Li
The paper introduces Connected Self Forcing, a training framework that reconnects gradient paths across autoregressive video chunks to improve long‑horizon visual quality and temporal consistency. It allows feedback from later predictions to influence earlier context generation, using shortcut gradient replay to keep memory usage manageable. The method is combined with distribution‑matching distillation and shows experimental gains without altering the inference procedure.
By Dongbin Zhang, Chaoda Zheng, Kangjie Chen, Xiangyu Li, Shijia Chen, Jinhao Deng, Yuqi Zhang, Guangfeng Jiang, Hongbin Lin, Choo Sin Wai, Minqi Wang, Puyi Wang, Jingye Zhang, Yu Zhang, Xianming Liu, Boyang Wang