Pith. sign in

REVIEW 5 cited by

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2511.12940 v2 pith:5PKMDXMB submitted 2025-11-17 cs.CV

Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention

classification cs.CV
keywords memoryattentiongenerationrecurrentautoregressivediffusionlocalvideo
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

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.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 5 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Streaming Multi-Agent Autoregressive Diffusion Model with World State Registers

    cs.CV 2026-07 conditional novelty 6.0

    Adding persistently updated, supervised world-state register tokens to streaming multi-agent diffusion improves cross-agent consistency and visual quality in two-agent Minecraft generation.

  2. Echo-Memory: A Controlled Study of Memory in Action World Models

    cs.CV 2026-06 unverdicted novelty 6.0

    A controlled study finds that block-wise state-space recurrence outperforms other memory designs for open-domain scene return in action-conditioned video models, and that standard replay metrics do not adequately meas...

  3. From Pixels to States: Rethinking Interactive World Models as Game Engines

    cs.CV 2026-07 conditional novelty 5.0

    Interactive world models are reorganized around the game-engine action-state-observation loop, and a 90-hour Black Myth: Wukong dataset with frame-aligned actions, ground-truth states, and observations is introduced.

  4. AlayaWorld: Long-Horizon and Playable Video World Generation

    cs.CV 2026-07 conditional novelty 4.0

    AlayaWorld is a full-stack open-source framework for interactive video world generation, combining 3D spatial caching, error-bank training, and few-step distillation for real-time playable worlds.

  5. Reinforcement Learning: From Algorithms To Foundation Models

    cs.AI 2026-07 conditional novelty 3.0

    A dissertation uniting the author's published results: non-exploitable Nash-DQN policies and the FightLadder benchmark for games, plus diffusion/consistency-model world models for RL — a compilation rather than new results.