LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation

• URL: http://arxiv.org/abs/2608.28460v1
• Date: Fri, 28 Aug 2026 15:49:13 GMT
• Title: LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
• Abstract summary: Autoregressive video diffusion produces chunks from a bounded recent context.<n>Recency-based caching evicts historical cues needed when subjects, objects, scenes, or attributes reappear.<n>LayerRecall retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers.
• Score: 22.878882105342182
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding [64.34948094316685]
  We introduce LatentStream, a progressive latent working memory framework that shifts streaming memory from store-and-retrieve to retrieve-and-internalize.<n>LatentStream achieves new state-of-the-art results on existing online and offline video benchmarks.
  arXiv  Detail & Related papers  (2026-09-03T17:28:14Z)
• MARCH: Scaling Recurrent Memory with Content-Routed State Anchors [41.39470291507015]
  Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length.<n>Recurrent alternatives offer efficient decoding by compressing the entire history into a fixed-size state.<n>We introduce Memory-Anchor Routing across Context History (MARCH), a network architecture that effectively scales state-space models beyond a fixed-size dimension.
  arXiv  Detail & Related papers  (2026-08-12T13:45:01Z)
• MemOps: Benchmarking Lifecycle Memory Operations in Long-Horizon Conversations [50.24315431387575]
  We introduce MemOps, a benchmark that reformulates conversational memory as a sequence of lifecycle operations.<n>MemOps represents each memory event with a structured trace specifying its trigger, target, scope, state transition, and supporting evidence.<n>Across long-context, retrieval-based, parametric and managed-memory systems, MemOps disentangles failure modes that final-answer accuracy alone conceals.
  arXiv  Detail & Related papers  (2026-07-14T15:33:44Z)
• What Should a Streaming Video Model Remember? [28.189301152079214]
  Streaming video understanding models must answer queries at any moment during an ongoing stream, using only what they have observed so far and under fixed memory and computation budgets.<n>We propose textbfSelectStream, a selective latent-memory framework that keeps the current observation directly visible to a frozen VLM while exposing historical information only through a compact, query-conditioned evidence budget.<n> Experimental results show that SelectStream achieves strong online streaming performance and preserves general video understanding, reaching 82.67% on StreamingBench, 67.03% on OVO-Bench, and 74.4% average accuracy on offline video benchmarks
  arXiv  Detail & Related papers  (2026-06-15T07:50:19Z)
• TetherCache: Stabilizing Autoregressive Long-Form Video Generation with Gated Recall and Trusted Alignment [51.33418612284208]
  We propose TetherCache, a training-free and plug-and-play cache management strategy for drift-resistant long video generation.<n>Gated Recall with Attention-Diversity Balancing selects long-range memory frames using a gated score.<n>TAME lightly edits newly recalled memory tokens by aligning their statistics to a trusted context distribution.
  arXiv  Detail & Related papers  (2026-06-11T08:16:08Z)
• FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video Diffusion [59.207505503284715]
  FadeMem organizes historical KV blocks into a temporal hierarchy under a fixed cache budget.<n>New history is inserted as fine-grained entries, while older adjacent entries are progressively merged.<n>Experiments show improved subject consistency, background stability, and temporal coherence over existing bounded-cache strategies.
  arXiv  Detail & Related papers  (2026-06-09T10:22:18Z)
• SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation [30.157534925157844]
  SlotMemory is an object-centric Key-Value memory mechanism for streaming video diffusion.<n>Our approach shifts the memory abstraction from "when" an event occurred to "what" is being represented by decomposing the transformer's key-value manifold.
  arXiv  Detail & Related papers  (2026-05-29T09:04:26Z)
• Echo-Forcing: A Scene Memory Framework for Interactive Long Video Generation [48.476317015122625]
  Echo-Forcing is a training-free scene memory framework for interactive long video generation.<n>It supports smooth transitions, hard cuts, and long-range scene recall under a bounded cache budget.
  arXiv  Detail & Related papers  (2026-05-15T14:33:09Z)
• Mixture of Contexts for Long Video Generation [72.96361488755986]
  We recast long-context video generation as an internal information retrieval task.<n>We propose a simple, learnable sparse attention routing module, Mixture of Contexts (MoC), as an effective long-term memory retrieval engine.<n>As we scale the data and gradually sparsify the routing, the model allocates compute to salient history, preserving identities, actions, and scenes over minutes of content.
  arXiv  Detail & Related papers  (2025-08-28T17:57:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.