arXiv 2605.210282026-08-03cs.CVcs.AI

DySink：动态帧 sinks 用于自回归长视频生成

DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation

School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Lab. of Computer Network and Information Integration, Southeast University（东南大学计算机网络与信息集成重点实验室）；Zhongguancun Academy（中关村学院）；Zhongguancun Institute of Artificial Intelligence（中关村人工智能研究院）；Institute of Automation, CAS（中国科学院自动化研究所）

Bo Ye, Xinyu Cui, Jian Zhao, Tong Wei, Min-Ling Zhang

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出 DySink，一种基于检索的框架，通过维护紧凑的记忆银行并选择视觉相关的历史帧作为动态帧 sinks，以提高自回归长视频生成的动态性和时间质量。

摘要：

自回归长视频生成通常采用有界内存流以提高效率，通常结合局部窗口实现短期连续性与静态早期帧 sinks 作为长程锚点。然而，这种固定分配在当前视觉状态与早期帧大幅偏离时仍会缓存早期帧，而丢弃可能更相关的中间历史。结果，保留的长程上下文可能变得不适应，并偏向过时的线索；在严重情况下，RoPE 引起的相位再对齐会homogenize 头间注意力并导致 sink 崩溃，其中内容会回归到 sink 帧。我们提出 DySink，一种基于检索的框架，维护紧凑的记忆银行并选择视觉相关的历史帧作为动态帧 sinks。DySink 将自适应检索与 sink 异常门相结合，后者检测检索上下文中的过度头间共识并抑制易崩溃的上下文。在分钟级视频上的实验表明，DySink 在动态度方面一致优于强基线，同时也实现了更高的时间质量。代码和模型权重将在 https://github.com/yebo0216best/DySink 上发布。

英文摘要：

Autoregressive long video generation often adopts bounded-memory streaming for efficiency, typically combining local windows for short-term continuity with static early-frame sinks as long-range anchors. However, this fixed allocation keeps early frames cached even when the current visual state has substantially diverged from them, while discarding potentially more relevant intermediate history. As a result, the retained long-range context may become less adaptive and bias generation toward outdated cues; in severe cases, RoPE-induced phase re-alignment can homogenize inter-head attention and cause sink collapse, where content regresses toward sink frames. We propose DySink, a retrieval-based framework that maintains a compact memory bank and selects visually relevant historical frames as dynamic frame sinks. DySink couples adaptive retrieval with a sink anomaly gate that filters retrieved context exhibiting excessive inter-head consensus, an attention pattern associated with sink collapse. Experiments on 50--100-second videos show that DySink achieves the highest measured temporal quality among the evaluated autoregressive baselines, while retaining competitive text alignment and framewise quality. The code is available at https://github.com/yebo0216best/DySink.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。