aiqbench analysis
This research introduces Diffusion ReRoll, a novel framework for robotic sequential prediction that improves upon standard diffusion models by enabling iterative cross-horizon revision of action sequences. By selectively re-noising locally stable regions while others continue denoising, the method achieves significant gains in success rates on long-horizon planning and multi-task benchmarks compared to existing causal or full-sequence approaches. The work demonstrates how structured revisable denoising enhances policy learning and out-of-distribution robustness for advanced robotic control systems.
Diffusion ReRoll: Revisable Denoising for Robotic Sequential Prediction
arXiv:2607.19919v1 Announce Type: new Abstract: 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 have become locally stable 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, and unified video-action modeling. 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 matched 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 the LIBERO-10 multi-task benchmark. 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. These results support structured re-noising as an effective mechanism for revisable robotic sequence generation.
Abstract: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 have become locally stable 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, and unified video-action modeling. 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 matched 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 the LIBERO-10 multi-task benchmark. 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. These results support structured re-noising as an effective mechanism for revisable robotic sequence generation.
Robotics (cs.RO); Machine Learning (cs.LG)
arXiv:2607.19919 [cs.RO]
(or arXiv:2607.19919v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.19919 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 294 words
Related coverage
DiffusionGemma: Google’s Diffusion-Based Open Model for Faster Text Generation
Analytics Vidhya · Jun 11, 2026
Adaptive Mean Flow for Responsive Closed-Loop Robot Control
arXiv · Oct 7, 2026
Flow Reasoning Models: Turning Discrete Flows Into Efficient Recurrent Reasoners
arXiv · Sep 1, 2026
DFlash Speculative Decoding on AMD Instinct MI355X: Up to 5× Faster Qwen3.5 Inference
AMD · Sep 16, 2026