# LayerRecall：面向长时视频一致性的状态条件记忆路由

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-08-28 08:00
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmtguy7ww0autrochslcaghr7
- 原文链接：https://arxiv.org/abs/2608.28460

## AI 摘要

LayerRecall 提出当前状态条件、按层选择的记忆路由机制，仅将检索到的历史 K/V 状态注入骨干网络中对记忆敏感的层，同时保留局部注意力。配合 Cross-Horizon Prediction Matching（CHPM）在预测空间监督有界记忆路由，减少对稀缺长视频和显式标注的依赖。

## 正文

Autoregressive video diffusion enables scalable long-video generation by producing chunks from a bounded recent context. While recency-based caching preserves local continuity, it evicts historical cues needed when subjects, objects, scenes, or attributes reappear. Existing memory mechanisms expose models to nonlocal history, but access alone does not ensure effective use. Our analysis reveals that video DiT layers exhibit distinct preferences for current, recent, and distant context, suggesting that long-range memory requires deciding both what to retrieve and where to use it. We introduce LayerRecall, a current-conditioned, layer-selective memory router that retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers while preserving local attention elsewhere. To reduce reliance on scarce high-quality long-horizon videos and explicit memory-allocation labels, we further propose Cross-Horizon Prediction Matching (CHPM), which uses a privileged long-context reference to supervise the bounded-memory router in prediction space. Across 100 multi-shot evaluation prompts, LayerRecall achieves the best overall results on MemoBench and MovieBench while matching its backbone on VBench-Long, demonstrating stronger long-range recovery without sacrificing local continuity. Qualitative analyses further reveal memory-guided self-correction, whereby initially mismatched local attributes return to their historical appearance without resetting ongoing motion or scene structure. Additional analyses show cross-backbone portability and negligible inference overhead.