arXiv Computer Vision
MosaiChunk: Compositing Spatio-Temporal Memory for Autoregressive Video Generation
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Aug 28
Tether the Subject, Release the Scene: Query-Aware Memory Routing for Long-Horizon Autoregressive Video Generation
The paper introduces TetherMem, a training‑free, query‑aware memory router designed for streaming autoregressive video models that generate long videos in chunks. By separating subject and scene queries and modulating historical access with region‑ and age‑conditioned priors, TetherMem prevents the model from anchoring the scene to stale backgrounds and viewpoints, a problem termed memory‑anchored scene under‑progression. In blinded pairwise evaluations, TetherMem outperforms eight baseline methods in overall quality and scene progression, and on full 30‑second videos it maintains background, viewpoint, and scene changes while preserving subject identity and temporal continuity.
arXiv Computer Vision
Aug 31
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
LayerRecall is a memory router for autoregressive video diffusion that selectively retrieves and injects historical key/value states into specific layers of the model, based on the current context. It addresses the problem that existing memory mechanisms expose nonlocal history but do not guarantee effective use, by recognizing that different layers prefer current, recent, or distant context. The method, combined with Cross‑Horizon Prediction Matching, achieves state‑of‑the‑art long‑range consistency on MemoBench and MovieBench while maintaining local continuity and incurring negligible inference overhead.
arXiv Machine Learning
Aug 10
Addressable Memory for Video World Models
arXiv:2608. 07408v1 Announce Type: cross Abstract: We study visual persistence in interactive video world models.
arXiv AI
Jun 9
DySink: Dynamic Frame Sinks for Autoregressive Long Video Generation
arXiv:2605. 21028v2 Announce Type: replace-cross Abstract: 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.
arXiv Computer Vision
3d ago
Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
arXiv:2605.25333v3 Announce Type: replace Abstract: Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption...
arXiv AI
Jun 12
TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment
arXiv:2606. 13035v1 Announce Type: cross Abstract: Autoregressive video diffusion models provide a natural formulation for streaming and variable-length video generation by conditioning newly generated frames on previously generated content.