Tether the Subject, Release the Scene: Query-Aware Memory Routing for Long-Horizon Autoregressive Video Generation

2026-08-27

AI Summary

为解决长视频生成中背景锁定问题，提出TetherMem方法，通过区分主题和场景查询来调节历史记忆访问，改善场景进展与整体质量。

Abstract

Streaming autoregressive video models generate long videos chunk by chunk, using historical memory to maintain consistency. Existing methods typically expose subject and scene queries to history through similar policies. This stabilizes the subject, but can also lock backgrounds, viewpoints, and scene structure to previously generated states even when local motion continues. We call this failure memory-anchored scene under-progression; consistency and motion metrics alone can miss it. We introduce TetherMem, a training-free, query-aware spatiotemporal memory router for frozen video generators. TetherMem separates subject and scene queries and modulates historical access with region- and age-conditioned priors: subject queries retain identity-bearing history, while scene queries reduce reliance on subject history and stale backgrounds. Across 2,400 blinded pairwise judgments from 10 annotators, TetherMem achieves the highest estimated expected preference among eight streaming long-video baselines for overall quality (0.780) and scene progression (0.769). On complete 30-second videos, it sustains changes in background, viewpoint, and scene state while preserving subject recognizability and temporal continuity.

Problem

• autoregressive video generation
• memory-anchored scene under-progression
• query-aware memory routing

Innovation

• TetherMem
• query-aware
• spatiotemporal memory router
• memory-anchored scene under-progression