Meanflow

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 23

All topics

Posterior sampling by source-space MCMC via prior-based few-step transport maps
Oct 1, 2026Hoang Phuc Hau Luu, Marcelo Hartmann, Zhongjian WangPosterior Sampling Markov Chain Monte Carlo
Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore. · Department of Computer Science, Faculty of Science, University of Helsinki, Finland.
Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Models
Oct 1, 2026Jiawei Fan, Sifeng Wang, Yuqing Hou +1Meanflow Multimodal Action Distributions
Intel Labs China · Midea AI Research
Acceleration of Diffusion Language Model through Discrete Average Generator
Sep 29, 2026Yidong Ouyang, Zhengyan Wan, Themis Haris +8Diffusion Language Models Few-Step Generation
University of California, Los Angeles · Google · Work done as a research intern at Google
MeanFlowAdvantage: Stable Reward Fine-Tuning for Few-Step Average-Velocity Generators
Sep 29, 2026Haocheng Tang, Tianchi Xie, Xingqiao LinMeanflow Generative Flow Networks
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 Policies 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 +1Posterior Sampling Bayesian Inverse Problems
WashU · UW-Madison
uFlowCSP: Crystal Structure Prediction using Mean flow generative models
Sep 9, 2026Sourin Dey, Dipannoy Das Gupta, Lai Wei +2Crystal Structure Prediction Crystal Structure
Department of Computer Science and Engineering University of South Carolina Columbia, SC 29201 · Department of Computer Science and Cybersecurity University of North Georgia Columbia, SC 29201
Ask Self, Ask Others: Relation Is All You Need
Aug 20, 2026Yuting Ge, Pengju Yang, Mingkai NieLinear Attention Block Sparse Flash Attention
Department of Electrical Engineering City University of Hong Kong · Jilin University · National University of Singapore
GraspMeanFlow: SE(3)-Equivariant MeanFlow for Few-Step 6-DoF Grasp Generation
Aug 4, 2026Jiyong Kwon, Yikun Bai, Amirhossein Mollaali +1Robotic Grasping Meanflow
School of Mechanical Engineering, Purdue University · Department of Mathematics, Purdue University
When Extreme Darkness Meets Motion Blur: MeanFlow for Unified RAW Restoration
Aug 3, 2026Zepu Wang, Jingze Liang, Weijie Xiao +1Low-Light Image Enhancement Motion Blur
University of Electronic Science and Technology of China
SE(3)-MeanFlow: Few-Step Protein Backbone Generation on Lie Groups
Jul 29, 2026Yikun Bai, Binghang Lu, Yikai Liu +7Meanflow Generative Models
Department of Mathematics, Purdue University · School of Electrical and Computer Engineering, Purdue University · Department of Biochemistry, Purdue University +5
Do Not Break the Vessels: Structure-Preserving Mean Flow for Vascular Image Translation
Jun 30, 2026Changjin Sun, Zhuo Hu, Kaini Wang +6Latent Transport Meanflow
School of Biological Science and Medical Engineering, Southeast University, Nanjing, China · School of Computer Science and Engineering, Southeast University, Nanjing, China · Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong, China +2
RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal Navigation
Jun 29, 2026Zixuan Zhang, Yuqi Chen, Junjie Gao +4Object Goal Navigation Flow Policies
Nanyang Technological University, Singapore
ReactVLA: Fast and Lightweight Reactive Robot Manipulation via Improved Mean Flow Action Generation
Jun 12, 2026Yanzhao Guo, Wenkai Chen, Jianwei ZhangDiffusion-Based Vision-Language-Actions Action Generation
Shanghai Jiao Tong University · Technical Aspects of Multimodal Systems (TAMS), Department of Informatics, Universität Hamburg
Score-Based One-step MeanFlow Policy Optimization
May 22, 2026Kyungyoon Kim, Donghyeon Ki, Hee-Jun Ahn +1Flow Policies 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 +3Meanflow Diffusion Models
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 +2Meanflow Generative Flow Networks
Department of Computer Science, University of Kentucky Lexington, Kentucky 40506, USA
Noise-Started One-Step Real-World Super-Resolution via LR-Conditioned SplitMeanFlow and GAN Refinement
May 10, 2026Wei Zhu, Kai Zhang, Yu Zheng +3Real-World Image Super-Resolution Meanflow
Nanjing University of Science and Technology · Nanjing University · Huawei
Physics-Informed Neural PDE Solvers via Spatio-Temporal MeanFlow
May 9, 2026Hanru Bai, Yuncheng Zhou, Difan ZouNeural Partial Differential Equation Solvers Time Discretization
1Fudan University · 2The University of Hong Kong.
RA-CMF: Region-Adaptive Conditional MeanFlow for CT Image Reconstruction
Apr 28, 2026Md Shifatul Ahsan Apurba, Md Selim, Jin ChenCone-Beam Computed Tomography Meanflow
Biomedical Informatics and Data Science University of Alabama at Birmingham Birmingham, AL, United States · Computer Science Florida Polytechnic University Lakeland, FL, United States
Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation
Apr 20, 2026Chenxi Zhao, Chen Zhu, Xiaokun Feng +6Few-Step Generation Text-Conditioned Diffusion Model
College of Computer Science, Nankai University · AMAP, Alibaba Group
Learning Hamiltonian Flow Maps: Mean Flow Consistency for Large-Timestep Molecular Dynamics
Jan 29, 2026Winfried Ripken, Michael Plainer, Gregor Lied +5Invertible Flows Hamiltonian
Technical University Berlin · BIFOLD · Free University of Berlin +6
FlowerDance: MeanFlow for Efficient and Refined 3D Dance Generation
Nov 26, 2025Kaixing Yang, Xulong Tang, Ziqiao Peng +4Human Motion Generation Duet
Renmin University of China · Malou Tech Inc · Wuhan University +1

Oct 1, 2026, stat.MLJ/K move · Enter open · S save

Posterior sampling by source-space MCMC via prior-based few-step transport maps

Hoang Phuc Hau Luu, Marcelo Hartmann, Zhongjian Wang

Division of Mathematical Sciences, School of Physical and Mathematical Sciences, Nanyang Technological University, Singapore. · Department of Computer Science, Faculty of Science, University of Helsinki, Finland.

Posterior Sampling Markov Chain Monte Carlo Prior Knowledge Integration Meanflow Monte Carlo

Open paper AskPDF arXiv

Bayesian inference increasingly uses informative but implicit priors represented only by samples, such as historical ensembles, simulator outputs, and pretrained generative models. The same computational problem appears in the test-time guidance task (generalized Bayes), where an explicit positive weight, e.g., an exponentiated reward, tilts an implicit prior. We develop a framework for source-space generalized Bayesian inference that combines inexpensive few-step prior transports with posterior stability guarantees. Specifically, we represent the prior using a one- or few-step improved MeanFlow (iMF) map and perform posterior sampling in its Gaussian source space. We establish Wasserstein error bounds between the exact and learned posteriors in terms of the joint population iMF and auxiliary-velocity loss, decomposed into training suboptimality and model-class approximation error. In the iMF source space, we adopt parallel tempering with preconditioned Crank-Nicolson updates and introduce a hybrid variant that incorporates split Hamiltonian Monte Carlo to improve sampling efficiency. Synthetic experiments show that the proposed framework can approximate posterior distributions accurately and efficiently, while CLIP-guided ImageNet experiments demonstrate its ability to steer a pretrained iMF image prior toward text-specified preferences.

Momentum

Related topics

Latest papers 23