MeanFlow

Follow this topic Ask about this topic

Momentum

4 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 16

All topics

Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Flow Matching Robot Foundation Models
Intel Labs China · Midea AI Research
MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
Sep 29, 2026Haocheng Tang, Tianchi Xie, Xingqiao LinFlow Matching MeanFlow
Northeastern University Boston, MA 02115, USA · Tsinghua University Beijing, 100084, PRC · Carnegie Mellon University Pittsburgh, PA 15213, USA
QAMM: Adjoint MeanFlow Matching for Few-Step Offline Reinforcement Learning
Sep 28, 2026Yuehu Gong, Shutong Ding, Mokai Pan +4Flow Matching MeanFlow
School of Data Science, Fudan University · ShanghaiTech University · Shanghai Innovation Institute
SNaP: One-Step Posterior Sampling for Noisy Inverse Problems
Sep 28, 2026Shirin Shoushtari, Edward P. Chandler, Xiao Shi +1Flow Matching MeanFlow
WashU · UW-Madison
FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow
Sep 3, 2026Byeongjun Park, Byung-Hoon Kim, Hyungjin ChungFlow Matching Camera-Controlled Video Generation
EverEx · Yonsei University · Korea University
Quantum MeanFlow: single-shot generative sampling on NISQ hardware
Sep 2, 2026Ashish Joshi, Eshaan Mistry, Takahiko KoyamaQuantum Generative Modeling Flow Matching
1Human Biology-Microbiome-Quantum Research Center (WPI-Bio2Q), Keio University, Tokyo, Japan · 2Keio University Sustainable Quantum Artificial Intelligence Center (KSQAIC), Keio University, Tokyo, Japan · University of California, Berkeley, CA, USA
NavCMPO: Critic-Guided MeanFlow Policy Optimization for Adaptive Navigation
Jul 16, 2026Junjie An, Yi Wu, Xiao Liu +5Flow Matching Robot Policy Adaptation
Zhejiang University, Hangzhou, China · Shandong University
MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation
Jun 8, 2026Dohwan Kim, Jung-Woo ChoiFlow Matching MeanFlow
School of Electrical Engineering, KAIST, Daejeon, Republic of Korea
Score-Based One-step MeanFlow Policy Optimization
May 22, 2026Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn +1Flow Matching MeanFlow
Korea University, Decision Making Lab · Gauss Labs Inc.
Stabilizing, Scaling & Enhancing MeanFlow for Large-scale Diffusion Distillation
May 18, 2026Xiao He, Yang Li, Peizhen Zhang +3Flow Matching Diffusion Model Distillation
1State Key Laboratory of Integrated Services Networks, Xidian University · 2Tencent Hunyuan
Discrete MeanFlow: One-Step Generation via Conditional Transition Kernels
May 12, 2026Fairoz Nower Khan, Nabuat Zaman Nahim, Md Sajid Ahmed +2Markov Models MeanFlow
Department of Computer Science, University of Kentucky Lexington, Kentucky 40506, USA
On Variance Reduction in Learning Mean Flows
May 10, 2026Juanwu Lu, Ziran WangFlow Matching MeanFlow
Purdue University
Physics-Informed Neural PDE Solvers via Spatio-Temporal MeanFlow
May 9, 2026Hanru Bai, Yuncheng Zhou, Difan ZouFlow Matching Neural PDE Solvers
1Fudan University · 2The University of Hong Kong.
Stochastic Transition-Map Distillation for Fast Probabilistic Inference
May 8, 2026George Rapakoulias, Peter Garud, Lingjiong Zhu +1Diffusion Model Distillation MeanFlow
Department of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA · Department of Computer Science, Georgia Institute of Technology, Atlanta, GA · Department of Mathematics, Florida State University, Tallahassee, FL
Mean Flow Policy Optimization
Apr 16, 2026Xiaoyi Dong, Xi Sheryl Zhang, Jian ChengMeanFlow Mean Flow
C2DL, Institute of Automation, Chinese Academy of Sciences · School of Artificial Intelligence, University of Chinese Academy of Sciences · AiRiA +1
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
Nov 26, 2025Kaixing Yang, Xulong Tang, Ziqiao Peng +4MeanFlow Human Motion Generation
Renmin University of China · Malou Tech Inc · Wuhan University +1

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

Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models

Jiawei Fan, Sifeng Wang, Yuqing Hou, Anbang Yao

Intel Labs China · Midea AI Research

Flow Matching Robot Foundation Models MeanFlow Efficient VLA Model Inference Robot Motion Generation Flow-Based Generative Modeling

Open paper AskPDF arXiv

In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a promising framework for this goal, yet its direct application leads to performance collapse. We discover that this stems from two distinctive dynamics exhibited in the RFM velocity field: (1) the ``local acceleration" exhibits stability early on, but surges sharply towards the end of the denoising process, and (2) the spread of its magnitudes across samples widens as denoising progresses. To address these issues, we introduce Kinematic MeanFlow (K-MF), a novel one-step action policy tailored for RFMs. Specifically, grounded in a kinematic identity, K-MF decouples the time derivative term in the MeanFlow formulation into two sub-interval terms separated by an intermediate point. This decoupled formulation enables the two terms to capture early-stage and late-stage denoising dynamics, respectively, while mitigating the error amplification across the process. As a result, our K-MF empowers RFMs to achieve one-step action generation in both training from scratch and fine-tuning paradigms across diverse tasks, while outperforming multi-step flow matching in most settings. In terms of inference efficiency, K-MF reduces action-head latency of GR00T-N1.6 by 67.5%~74.4% across L40 and Jetson Orin in eager and compiled modes, yielding end-to-end latency reductions of 30.3%~54.9%. Code will be available at https://github.com/IntelChina-AI/K-MF.

Momentum

Related topics

Latest papers 16