LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
Ranking
Overall
82
Content
90
Popularity
65
Observed public metrics from 1 member.
Merged summary
TL;DR - LayerRecall is a state-conditioned memory router that helps autoregressive video diffusion models recover relevant distant context by injecting retrieved historical K/V states into selected transformer layers. It improves long-horizon consistency with negligible inference overhead while preserving local motion and scene continuity.
- Identifies distinct layer-level preferences for current, recent, and distant context in video diffusion transformers.
- Routes relevant historical states only to memory-sensitive layers, leaving local attention unchanged elsewhere.
- Uses Cross-Horizon Prediction Matching to train from a privileged long-context model without explicit memory-allocation labels.
- Achieves the best reported overall results on MemoBench and MovieBench across 100 multi-shot prompts while matching its backbone on VBench-Long.
Sources (1)
LayerRecall: A State-Conditioned Memory Router for Long-Horizon Consistency in Video Generation
Public signals
Hugging Face upvotes 29
TL;DR - LayerRecall is a state-conditioned memory router that helps autoregressive video diffusion models recover relevant distant context by injecting retrieved historical K/V states into selected transformer layers. It improves long-horizon consistency with negligible inference overhead while preserving local motion and scene continuity.
- Identifies distinct layer-level preferences for current, recent, and distant context in video diffusion transformers.
- Routes relevant historical states only to memory-sensitive layers, leaving local attention unchanged elsewhere.
- Uses Cross-Horizon Prediction Matching to train from a privileged long-context model without explicit memory-allocation labels.
- Achieves the best reported overall results on MemoBench and MovieBench across 100 multi-shot prompts while matching its backbone on VBench-Long.