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

arXiv: https://arxiv.org/abs/2608.28460 · HTML: https://mlsanity.com/paper/2608.28460/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 26 of its 27 references that are in the map.
- First posted on arXiv 28 Aug 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)

## Builds on (most cited first, 26 of 26)

- [CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer](https://mlsanity.com/paper/2408.06072/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text](https://mlsanity.com/paper/2403.14773/) (2024)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling](https://mlsanity.com/paper/2310.15169/) (2023)
- [Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval](https://mlsanity.com/paper/2506.03141/) (2025)
- [Long Context Tuning for Video Generation](https://mlsanity.com/paper/2503.10589/) (2025)
- [SANA-Video: Efficient Video Generation with Block Linear Diffusion Transformer](https://mlsanity.com/paper/2509.24695/) (2025)
- [FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention](https://mlsanity.com/paper/2407.19918/) (2024)
- [Infinity-RoPE: Action-Controllable Infinite Video Generation Emerges From Autoregressive Self-Rollout](https://mlsanity.com/paper/2511.20649/) (2025)
- [Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression](https://mlsanity.com/paper/2512.05081/) (2025)
- [Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing](https://mlsanity.com/paper/2411.16375/) (2024)
- [Context Forcing: Consistent Autoregressive Video Generation with Long Context](https://mlsanity.com/paper/2602.06028/) (2026)
- [VBench++: Comprehensive and Versatile Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2411.13503/) (2024)
- [MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives](https://mlsanity.com/paper/2512.14699/) (2025)
- [MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation](https://mlsanity.com/paper/2411.15262/) (2024)
- [SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation](https://mlsanity.com/paper/2410.23277/) (2024)
- [Efficient Autoregressive Video Diffusion with Dummy Head](https://mlsanity.com/paper/2601.20499/) (2026)
- [LongLive-RAG: A General Retrieval-Augmented Framework for Long Video Generation](https://mlsanity.com/paper/2606.02553/) (2026)
- [LongDiff: Training-Free Long Video Generation in One Go](https://mlsanity.com/paper/2503.18150/) (2025)
- [MemoBench: Benchmarking World Modeling in Dynamically Changing Environments](https://mlsanity.com/paper/2606.27537/) (2026)
- [SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation](https://mlsanity.com/paper/2605.31033/) (2026)
- [Composition of Memory Experts for Diffusion World Models](https://mlsanity.com/paper/2605.18813/) (2026)

## Built on by (most cited first, 4 of 4)

- [FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38839/) (2026)
- [LOCI: Spatial Linear Memory for Streaming World Models](https://mlsanity.com/paper/2609.40222/) (2026)
- [REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation](https://mlsanity.com/paper/2610.16632/) (2026)
- [GAD: Geometry Attention Distillation for Consistent Video Generation](https://mlsanity.com/paper/2610.18779/) (2026)

## Abstract (arXiv)

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.