# Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction

arXiv: https://arxiv.org/abs/2607.19919 · HTML: https://mlsanity.com/paper/2607.19919/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 40 references that are in the map.
- First posted on arXiv 22 Jul 2026.

## Builds on (most cited first, 30 of 38)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations](https://mlsanity.com/paper/2108.01073/) (2021)
- [LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning](https://mlsanity.com/paper/2306.03310/) (2023)
- [MaskGIT: Masked Generative Image Transformer](https://mlsanity.com/paper/2202.04200/) (2022)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Is Conditional Generative Modeling all you need for Decision-Making?](https://mlsanity.com/paper/2211.15657/) (2022)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots](https://mlsanity.com/paper/2406.02523/) (2024)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrations](https://mlsanity.com/paper/2310.17596/) (2023)
- [Efficient Diffusion Training via Min-SNR Weighting Strategy](https://mlsanity.com/paper/2303.09556/) (2023)
- [Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets](https://mlsanity.com/paper/2504.02792/) (2025)
- [OGBench: Benchmarking Offline Goal-Conditioned RL](https://mlsanity.com/paper/2410.20092/) (2024)
- [Video models are zero-shot learners and reasoners](https://mlsanity.com/paper/2509.20328/) (2025)
- [Unified Video Action Model](https://mlsanity.com/paper/2503.00200/) (2025)
- [History-Guided Video Diffusion](https://mlsanity.com/paper/2502.06764/) (2025)
- [AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation](https://mlsanity.com/paper/2305.09515/) (2023)
- [Rolling Diffusion Models](https://mlsanity.com/paper/2402.09470/) (2024)
- [Video Generators are Robot Policies](https://mlsanity.com/paper/2508.00795/) (2025)
- [Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models](https://mlsanity.com/paper/2401.03360/) (2023)
- [Large Video Planner Enables Generalizable Robot Control](https://mlsanity.com/paper/2512.15840/) (2025)
- [Generative Trajectory Stitching through Diffusion Composition](https://mlsanity.com/paper/2503.05153/) (2025)

## Built on by (most cited first, 5 of 5)

- [TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback](https://mlsanity.com/paper/2608.25798/) (2026)
- [ActionSplice: In-Flight Action Editing for Interactive World Models](https://mlsanity.com/paper/2609.08230/) (2026)
- [Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models](https://mlsanity.com/paper/2609.35439/) (2026)
- [Urgent Actions Go First: Urgency-Aware Denoising for Real-Time VLA Control](https://mlsanity.com/paper/2609.37772/) (2026)
- [Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence](https://mlsanity.com/paper/2610.18447/) (2026)

## Abstract (arXiv)

We propose Diffusion ReRoll, a diffusion-based framework for robotic sequential prediction that enables revisable denoising over horizons. Existing diffusion-based sequence predictors typically perform a single monotonic denoising process. In contrast, Diffusion ReRoll selectively re-noises regions that reach a predefined noise threshold while the remaining regions continue denoising, so the re-noised regions can be refined again using context from the rest of the horizon. This structured re-noising enables iterative cross-horizon revision, allowing earlier and later segments to revise one another, while maintaining local consistency. We evaluate Diffusion ReRoll against full-sequence diffusion and causal denoising based on Diffusion Forcing across long-horizon planning, policy learning, unified video-action modeling, and real-world navigation. On OGBench PointMaze and AntMaze, Diffusion ReRoll achieves relative gains in average success rate of 21% over Diffusion Forcing in matched guidance-based planning and 23% over Diffuser in goal-inpainting. In diffusion-policy-style action prediction, Diffusion ReRoll improves average success by 56.5% relative to Diffusion Policy across different prediction horizons and history lengths on LIBERO-10 under the official reset protocol. In unified video-action prediction, Diffusion ReRoll improves policy and inverse dynamics performance, especially under out-of-distribution evaluation, and achieves the best action-video consistency. Real-world navigation further demonstrates improved success under visual distribution shifts with onboard inference. These results show that structured re-noising enables cross-horizon revision and improves performance across robotic sequential prediction tasks.