Diffusion Policy

Follow this topic Ask about this topic

Momentum

22 papers in the last four weeks, up 450% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 134

All topics

Recovering Hidden Reward in Diffusion-Based Policies
May 1, 2026Yanbiao Ji, Qiuchang Li, Yuting Hu +7Reinforcement Learning Diffusion Policy
Shanghai Jiao Tong University · KOKONI 3D
DiscreteRTC: Discrete Diffusion Policies are Natural Asynchronous Executors
Apr 27, 2026Pengcheng Wang, Kaiwen Hong, Chensheng Peng +4Diffusion Policy Robotic Manipulation
UC Berkeley1 · UIUC2 · UT Austin3 +1
Tube Diffusion Policy: Reactive Visual-Tactile Policy Learning for Contact-rich Manipulation
Apr 26, 2026Teng Xue, Alberto Rigo, Bingjian Huang +4Robot Policy Learning Contact-Rich Robotic Manipulation
Meta Reality Labs Research · Idiap Research Institute · École Polytechnique Fédérale de Lausanne (EPFL) +2
From Noise to Intent: Anchoring Generative VLA Policies with Residual Bridges
Apr 23, 2026Yiming Zhong, Yaoyu He, Zemin Yang +5Diffusion Policy Robot Motion Generation
ShanghaiTech University, Shanghai, China · Morphic Robotics, Shenzhen, China · The Chinese University of Hong Kong, Hong Kong, China.
FASTER: Value-Guided Sampling for Fast RL
Apr 21, 2026Perry Dong, Alexander Swerdlow, Dorsa Sadigh +1Diffusion Sampling Diffusion Policy
Stanford University
Accelerating trajectory optimization with Sobolev-trained diffusion policies
Apr 21, 2026Théotime Le Hellard, Franki Nguimatsia Tiofack, Quentin Le Lidec +1Trajectory Optimization Trajectory Generation
Inria - Département d’Informatique de l’École normale supérieure, PSL Research University, France · Courant Institute, New York University, USA
VADF: Vision-Adaptive Diffusion Policy Framework for Efficient Robotic Manipulation
Apr 17, 2026Xinglei Yu, Zhenyang Liu, Shufeng Nan +2Adaptive Inference Diffusion Policy
Fudan University · Shanghai Innovation Institute
R3D: Revisiting 3D Policy Learning
Apr 16, 2026Zhengdong Hong, Shenrui Wu, Haozhe Cui +83D ViTs Visuomotor Policy Learning
Zhejiang University · ShanghaiTech University
TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control
Jan 21, 2026Yuteng Sun, Haoran Wang, Ruofei Bai +4Robotic Control Diffusion Policy
Institute for Infocomm Research (I2R), A*STAR, Singapore · 2Tsinghua University, Beijing, China · 3Nanyang Technological University, Singapore
ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
Dec 17, 2025Wenlong Xia, Jinhao Zhang, Ce Zhang +6Robot Skill Learning Visuomotor Policy Learning
[cs.RO]
Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning
Dec 1, 2025Sebastian Sanokowski, Kaustubh Patil, Majid KhadivRL Control Diffusion Policy
Munich Institute of Robotics and Machine Intelligence (MIRMI), Technical University Munich · Practical Project Student Exchange Program, Technical University Munich · MIT World Peace University
PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork
Nov 10, 2025Hohei Chan, Xinzhi Zhang, Antao Xiang +2Multi-Agent Coordination Multi-Agent Collaboration
School of Software Engineering, South China University of Technology, Guangzhou, China · Shanghai Jiao Tong University, Shanghai, China
Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
Aug 8, 2025Zhanyi Sun, Shuran SongVisuomotor Policy Learning Diffusion Policy
Stanford University
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
Date pendingDayi Dong, Maulik Bhatt, Seoyeon Choi +1Multi-Agent Coordination Diffusion Policy
Department of Mechanical Engineering, University of California Berkeley, Berkeley, CA 94709, USA

May 1, 2026, cs.ROJ/K move · Enter open · S save

Recovering Hidden Reward in Diffusion-Based Policies

Yanbiao Ji, Qiuchang Li, Yuting Hu, Shaokai Wu+6

Shanghai Jiao Tong University · KOKONI 3D

Reinforcement Learning Diffusion Policy Energy-Based Models

Open paper AskPDF arXiv

This paper introduces EnergyFlow, a framework that unifies generative action modeling with inverse reinforcement learning by parameterizing a scalar energy function whose gradient is the denoising field. We establish that under maximum-entropy optimality, the score function learned via denoising score matching recovers the gradient of the expert's soft Q-function, enabling reward extraction without adversarial training. Formally, we prove that constraining the learned field to be conservative reduces hypothesis complexity and tightens out-of-distribution generalization bounds. We further characterize the identifiability of recovered rewards and bound how score estimation errors propagate to action preferences. Empirically, EnergyFlow achieves state-of-the-art imitation performance on various manipulation tasks while providing an effective reward signal for downstream reinforcement learning that outperforms both adversarial IRL methods and likelihood-based alternatives. These results show that the structural constraints required for valid reward extraction simultaneously serve as beneficial inductive biases for policy generalization. The code is available at https://github.com/sotaagi/EnergyFlow.

Momentum

Related topics

Latest papers 134