English
Related papers

Related papers: One Step Is Enough: Dispersive MeanFlow Policy Opt…

200 papers

Consistency-based generative models like Shortcut and MeanFlow achieve impressive results via a target-aware design for solving the Probability Flow ODE (PF-ODE). Typically, such methods introduce a target time $r$ alongside the current…

Machine Learning · Computer Science 2026-02-23 Peng Sun , Xinyi Shang , Tao Lin , Zhiqiang Shen

Flow-based image generative models exhibit stable training and produce high quality samples when using multi-step sampling procedures. One-step generative models can produce high quality image samples but can be difficult to optimize as…

Machine Learning · Computer Science 2026-04-13 Chia-Hong Hsu , Frank Wood

Group Relative Policy Optimization has emerged as essential for aligning video diffusion models with human preferences, but faces a critical computational bottleneck: training a 14B parametered model typically demands hundreds of GPU days…

Computer Vision and Pattern Recognition · Computer Science 2026-05-18 Xiaoxuan He , Siming Fu , Zeyue Xue , Weijie Wang , Ruizhe He , Yuming Li , Dacheng Yin , Shuai Dong , Haoyang Huang , Hongfa Wang , Nan Duan , Bohan Zhuang

Diffusion policies have achieved great success in online reinforcement learning (RL) due to their strong expressive capacity. However, the inference of diffusion policy models relies on a slow iterative sampling process, which limits their…

Machine Learning · Computer Science 2025-10-17 Tianyi Chen , Haitong Ma , Na Li , Kai Wang , Bo Dai

We propose a principled and effective framework for one-step generative modeling. We introduce the notion of average velocity to characterize flow fields, in contrast to instantaneous velocity modeled by Flow Matching methods. A…

Machine Learning · Computer Science 2025-05-20 Zhengyang Geng , Mingyang Deng , Xingjian Bai , J. Zico Kolter , Kaiming He

Recent studies have shown the great potential of diffusion models in improving reinforcement learning (RL) by modeling complex policies, expressing a high degree of multi-modality, and efficiently handling high-dimensional continuous…

Robotics · Computer Science 2025-05-14 Huiyun Jiang , Zhuang Yang

This paper proposes an image-based robot motion planning method using a one-step diffusion model. While the diffusion model allows for high-quality motion generation, its computational cost is too expensive to control a robot in real time.…

Robotics · Computer Science 2025-04-29 Tomoharu Aizu , Takeru Oba , Yuki Kondo , Norimichi Ukita

Offline-to-online reinforcement learning (O2O-RL) has emerged as a promising paradigm for safe and efficient robotic policy deployment but suffers from two fundamental challenges: limited coverage of multimodal behaviors and distributional…

Robotics · Computer Science 2025-11-14 Haidong Huang , Haiyue Zhu. Jiayu Song , Xixin Zhao , Yaohua Zhou , Jiayi Zhang , Yuze Zhai , Xiaocong Li

Online off-policy reinforcement learning (RL) is shaped by two coupled choices: the policy class and the update rule. Gaussian policies are fast and have tractable entropy, but struggle with multimodal action distributions. Generative…

Machine Learning · Computer Science 2026-05-22 Zeyuan Wang , Da Li , Yulin Chen , Yuehu Gong , Yanming Guo , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast…

Machine Learning · Computer Science 2025-11-18 Zeyuan Wang , Da Li , Yulin Chen , Ye Shi , Liang Bai , Tianyuan Yu , Yanwei Fu

Learning expressive and efficient policy functions is a promising direction in reinforcement learning (RL). While flow-based policies have recently proven effective in modeling complex action distributions with a fast deterministic sampling…

Machine Learning · Computer Science 2026-03-10 Guojian Zhan , Letian Tao , Pengcheng Wang , Yixiao Wang , Yiheng Li , Yuxin Chen , Hongyang Li , Masayoshi Tomizuka , Shengbo Eben Li

Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the…

Recent advances in FlowMatching-based Vision-Language-Action (VLA) frameworks have demonstrated remarkable advantages in generating high-frequency action chunks, particularly for highly dexterous robotic manipulation tasks. Despite these…

Robotics · Computer Science 2026-03-03 Yang Chen , Xiaoguang Ma , Bin Zhao

This research gauges the ability of deep reinforcement learning (DRL) techniques to assist the optimization and control of fluid mechanical systems. It combines a novel, "degenerate" version of the proximal policy optimization (PPO)…

Optimization and Control · Mathematics 2021-05-19 H. Ghraieb , J. Viquerat , A. Larcher , P. Meliga , E. Hachem

Diffusion policies are a powerful paradigm for robotic control, but fine-tuning them with human preferences is fundamentally challenged by the multi-step structure of the denoising process. To overcome this, we introduce a Unified Markov…

Robotics · Computer Science 2026-02-03 Amitesh Vatsa , Zhixian Xie , Wanxin Jin

We present a comprehensive comparative study of three generative modeling paradigms: Denoising Diffusion Probabilistic Models (DDPM), Conditional Flow Matching (CFM), and MeanFlow. While DDPM and CFM require iterative sampling, MeanFlow…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Umang Agarwal , Rudraksh Sangore , Sumit Laddha

One-step generative modeling seeks to generate high-quality data samples in a single function evaluation, significantly improving efficiency over traditional diffusion or flow-based models. In this work, we introduce Modular MeanFlow (MMF),…

Machine Learning · Computer Science 2025-08-26 Haochen You , Baojing Liu , Hongyang He

Sampling from unnormalized target distributions is a fundamental yet challenging task in machine learning and statistics. Existing sampling algorithms typically require many iterative steps to produce high-quality samples, leading to high…

Machine Learning · Statistics 2026-02-27 Pascal Jutras-Dube , Jiaru Zhang , Ziran Wang , Ruqi Zhang

Diffusion-based models for robotic control, including vision-language-action (VLA) and vision-action (VA) policies, have demonstrated significant capabilities. Yet their advancement is constrained by the high cost of acquiring large-scale…

Flow matching has emerged as a competitive framework for learning high-quality generative policies in robotics; however, we find that generalisation arises and saturates early along the flow trajectory, in accordance with recent findings in…

Robotics · Computer Science 2026-03-03 Zidong Chen , Zihao Guo , Peng Wang , ThankGod Itua Egbe , Yan Lyu , Chenghao Qian