解决视频生成中交互场景下的记忆混乱问题，让模型能准确记住旧场景并快速响应新提示。
Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation
- 分层时序记忆分离稳定背景、历史片段和近期内容，避免干扰。
- 用结构化特征压缩历史场景，支持长时间回忆。
- 根据新旧场景差异智能遗忘冲突信息，适合交互式视频生成。
自回归视频扩散模型通过局部注意力和键值缓存实现开放式生成。然而，现有无需训练的长视频优化方法主要针对单一提示下的稳定扩展，难以应对涉及提示切换、旧场景遗忘和历史场景召回的交互场景。我们识别出核心瓶颈在于历史键值状态的功能耦合：稳定锚点与近期动态由同一缓存策略处理，导致背景过时污染、对新提示响应延迟、长期记忆丢失。为此，我们提出Echo-Forcing，一种无需训练的场景记忆框架，专为交互式长视频生成设计，包含三个核心机制：(1) 分层时序记忆，在相对RoPE下解耦稳定锚点、压缩历史与近期窗口；(2) 场景召回帧，将历史场景压缩为空间结构化的键值表示，支持长期召回；(3) 差异感知记忆衰减，根据新旧场景差异自适应遗忘冲突令牌。基于此，Echo-Forcing在有限缓存预算下统一支持平滑过渡、硬切和长程场景召回。在VBench-Long上的大量评估表明，其在长视频生成与交互式视频生成设置中均取得最佳综合表现。代码已开源：https://github.com/mingqiangWu/Echo-Forcing。
原文摘要 · Abstract (English)
Autoregressive video diffusion models enable open-ended generation through local attention and KV caching. However, existing training-free long-video optimization methods mainly focus on stable extension under a single prompt, making them difficult to handle interactive scenarios involving prompt switching, old scene forgetting, and historical scene recall. We identify the core bottleneck as the functional entanglement of historical KV states: stable anchors and recent dynamics are handled by the same cache policy, leading to outdated background contamination, delayed response to new prompts, and loss of long-range memory. To address this issue, we propose Echo-Forcing, a training-free scene memory framework specifically designed for interactive long video generation with three core mechanisms: (1) Hierarchical Temporal Memory, which decouples stable anchors, compressed history, and recent windows under relative RoPE; (2) Scene Recall Frames, which compresses historical scenes into spatially structured KV representations to support long-term recall; and (3) Difference-aware Memory Decay, which adaptively forgets conflicting tokens according to the discrepancy between old and new scenes. Based on these designs, Echo-Forcing uniformly supports smooth transitions, hard cuts, and long-range scene recall under a bounded cache budget. Extensive evaluations on VBench-Long further demonstrate that Echo-Forcing achieves the best overall performance in both long-video generation and interactive video generation settings. Our code is released in https://github.com/mingqiangWu/Echo-Forcing
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。