# Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

arXiv: https://arxiv.org/abs/2511.12940 · HTML: https://mlsanity.com/paper/2511.12940/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 48 of its 58 references that are in the map.
- First posted on arXiv 17 Nov 2025.

## Builds on (most cited first, 30 of 48)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Hierarchical Text-Conditional Image Generation with CLIP Latents](https://mlsanity.com/paper/2204.06125/) (2022)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Auto-Encoding Variational Bayes](https://mlsanity.com/paper/1312.6114/) (2013)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [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)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers](https://mlsanity.com/paper/2205.15868/) (2022)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Recurrent World Models Facilitate Policy Evolution](https://mlsanity.com/paper/1809.01999/) (2018)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Open-Sora: Democratizing Efficient Video Production for All](https://mlsanity.com/paper/2412.20404/) (2024)
- [GAIA-1: A Generative World Model for Autonomous Driving](https://mlsanity.com/paper/2309.17080/) (2023)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models](https://mlsanity.com/paper/2401.09047/) (2024)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Learning to (Learn at Test Time): RNNs with Expressive Hidden States](https://mlsanity.com/paper/2407.04620/) (2024)
- [Diffusion Models Are Real-Time Game Engines](https://mlsanity.com/paper/2408.14837/) (2024)
- [Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Images](https://mlsanity.com/paper/1506.07365/) (2015)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)

## Built on by (most cited first, 9 of 9)

- [Memorize-and-Generate: Towards Long-Term Consistency in Real-Time Video Generation](https://mlsanity.com/paper/2512.18741/) (2025)
- [Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers](https://mlsanity.com/paper/2607.21594/) (2026)
- [A Mechanistic View on Video Generation as World Models: State and Dynamics](https://mlsanity.com/paper/2601.17067/) (2026)
- [Echo-Memory: A Controlled Study of Memory in Action World Models](https://mlsanity.com/paper/2606.09803/) (2026)
- [AlayaWorld: Long-Horizon and Playable Video World Generation](https://mlsanity.com/paper/2607.06291/) (2026)
- [From Pixels to States: Rethinking Interactive World Models as Game Engines](https://mlsanity.com/paper/2607.14076/) (2026)
- [R2M-Bench: Evaluating Revisit Memory via Relative Consistency in Interactive Video World Models](https://mlsanity.com/paper/2608.27328/) (2026)
- [Can Video World Models Track Unobserved World States?](https://mlsanity.com/paper/2608.30692/) (2026)
- [Reinforcement Learning: From Algorithms To Foundation Models](https://mlsanity.com/paper/2607.17560/) (2026)

## Abstract (arXiv)

Recent advancements in video generation has shifted from bidirectional models for short videos to autoregressive ones for ultra long video generation. Previous models, which usually use sliding window attention to restrict inference cost, lack effective memory compression and retrieval for long-term generation beyond the window size, leading to issues of forgetting and spatiotemporal inconsistencies. To enhance the retention of historical information with a fixed memory budget, we additionally incorporate temporal recurrent neural network (RNN) layers into the diffusion transformer (DiT) model. Specifically, we found that a LSTM layer after attention at each DiT layer achieves comparable performance to other state-of-the-art RNN blocks, such as Test-Time Training (TTT) and Mamba2. Moreover, existing diffusion-RNN approaches often suffer from performance degradation due to training-inference gap or the lack of overlap across windows. To address these limitations, we propose a novel Recurrent Autoregressive Diffusion (RAD) framework, which leverages recurrent blocks for memory update and retrieval and preserves local details by full attention on overlapping sliding windows, with no training and inference gap. Experiments on Memory Maze and Minecraft datasets demonstrate the superiority for long video generation by our framework with global memory and local attention.