English
Related papers

Related papers: Boosting Maximum Entropy Reinforcement Learning vi…

200 papers

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

Flow matching has emerged as a powerful generative framework, with recent few-step methods achieving remarkable inference acceleration. However, we identify a critical yet overlooked limitation: these models suffer from severe diversity…

Machine Learning · Computer Science 2026-04-15 Yexiong Lin , Jia Shi , Shanshan Ye , Wanyu Wang , Yu Yao , Tongliang Liu

Maximum entropy has become a mainstream off-policy reinforcement learning (RL) framework for balancing exploitation and exploration. However, two bottlenecks still limit further performance improvement: (1) non-stationary Q-value estimation…

Machine Learning · Computer Science 2025-11-18 Guojian Zhan , Likun Wang , Pengcheng Wang , Feihong Zhang , Jingliang Duan , Masayoshi Tomizuka , Shengbo Eben Li

We introduce Discrete flow Matching policy Optimization (DoMinO), a unified framework for Reinforcement Learning (RL) fine-tuning Discrete Flow Matching (DFM) models under a broad class of policy gradient methods. Our key idea is to view…

Machine Learning · Computer Science 2026-04-09 Maojiang Su , Po-Chung Hsieh , Weimin Wu , Mingcheng Lu , Jiunhau Chen , Jerry Yao-Chieh Hu , Han Liu

Mean flow (MeanFlow) enables efficient, high-fidelity image generation, yet its single-function evaluation (1-NFE) generation often cannot yield compelling results. We address this issue by introducing RMFlow, an efficient multimodal…

Machine Learning · Computer Science 2026-02-03 Yuhao Huang , Shih-Hsin Wang , Andrea L. Bertozzi , Bao Wang

Flow-matching policies hold great promise for reinforcement learning (RL) by capturing complex, multi-modal action distributions. However, their practical application is often hindered by prohibitive inference latency and ineffective online…

Machine Learning · Computer Science 2026-03-17 He Zhang , Ying Sun , Hui Xiong

Parameter estimation in Markov random fields (MRFs) is a difficult task, in which inference over the network is run in the inner loop of a gradient descent procedure. Replacing exact inference with approximate methods such as loopy belief…

Machine Learning · Computer Science 2012-06-18 Varun Ganapathi , David Vickrey , John Duchi , Daphne Koller

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is a crucial component for dLLMs to…

Machine Learning · Computer Science 2026-02-24 Yuchen Zhu , Wei Guo , Jaemoo Choi , Petr Molodyk , Bo Yuan , Molei Tao , Yongxin Chen

Distribution Matching Distillation (DMD) facilitates efficient inference by distilling multi-step diffusion models into few-step variants. Concurrently, Reinforcement Learning (RL) has emerged as a vital tool for aligning generative models…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Dengyang Jiang , Dongyang Liu , Zanyi Wang , Qilong Wu , Liuzhuozheng Li , Hengzhuang Li , Xin Jin , David Liu , Changsheng Lu , Zhen Li , Bo Zhang , Mengmeng Wang , Steven Hoi , Peng Gao , Harry Yang

Offline Reinforcement Learning (RL) learns optimal policies from fixed datasets, training a policy once and deploying it at inference time without further refinement. Inspired by model predictive control (MPC), we introduce an inference…

Machine Learning · Computer Science 2026-05-21 Rohan Deb , Stephen J. Wright , Arindam Banerjee

One-step generative modeling has emerged as a leading approach to amortize the inference cost of diffusion and flow-matching models. Among distillation-free methods, MeanFlow training is notoriously unstable, with non-decreasing loss and…

Machine Learning · Computer Science 2026-05-12 Juanwu Lu , Ziran Wang

While generative modeling has achieved remarkable success on tasks like natural language-conditioned image generation, enabling model adaptation from example data points remains a relatively underexplored and challenging problem. To this…

Machine Learning · Computer Science 2026-05-08 Tyler Ingebrand , Ruihan Zhao , Kushagra Gupta , David Fridovich-Keil , Sandeep P. Chinchali , Ufuk Topcu

Reliable value estimation serves as the cornerstone of reinforcement learning (RL) by evaluating long-term returns and guiding policy improvement, significantly influencing the convergence speed and final performance. Existing works improve…

Machine Learning · Computer Science 2025-10-28 Shan Zhong , Shutong Ding , He Diao , Xiangyu Wang , Kah Chan Teh , Bei Peng

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as an indispensable paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard policy optimization methods, such as Group Relative Policy…

Machine Learning · Computer Science 2026-02-09 Pengyi Li , Elizaveta Goncharova , Andrey Kuznetsov , Ivan Oseledets

Recent advances in large multi-modal generative models have demonstrated impressive capabilities in multi-modal generation, including image and video generation. These models are typically built upon multi-step frameworks like diffusion and…

Computer Vision and Pattern Recognition · Computer Science 2026-01-29 Zhenglin Cheng , Peng Sun , Jianguo Li , Tao Lin

There is growing interest in utilizing flow-based models as decision-making policies in reinforcement learning due to their high expressive capacity. However, effectively leveraging this expressivity for value maximization remains…

Machine Learning · Computer Science 2026-05-14 JaeHyeok Doo , Byeongguk Jeon , Seonghyeon Ye , Kimin Lee , Minjoon Seo

MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used as a latent MF by leveraging the pre-trained Stable…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Zheyuan Hu , Chieh-Hsin Lai , Ge Wu , Yuki Mitsufuji , Stefano Ermon

Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which…

Machine Learning · Statistics 2024-11-11 Nikita Kornilov , Petr Mokrov , Alexander Gasnikov , Alexander Korotin

This paper proposes a novel method, Explicit Flow Matching (ExFM), for training and analyzing flow-based generative models. ExFM leverages a theoretically grounded loss function, ExFM loss (a tractable form of Flow Matching (FM) loss), to…

Machine Learning · Computer Science 2024-07-03 Gleb Ryzhakov , Svetlana Pavlova , Egor Sevriugov , Ivan Oseledets

Denoising Diffusion Probabilistic Models (DDPMs) have established a new state-of-the-art in generative image synthesis, yet their deployment is hindered by significant computational overhead during inference, often requiring up to 1,000…

Machine Learning · Computer Science 2025-11-25 Srishti Gupta , Yashasvee Taiwade
‹ Prev 1 3 4 5 6 7 10 Next ›