English
Related papers

Related papers: Reverse Flow Matching: A Unified Framework for Onl…

200 papers

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

Diffusion probability models have shown significant promise in offline reinforcement learning by directly modeling trajectory sequences. However, existing approaches primarily focus on time-domain features while overlooking frequency-domain…

Machine Learning · Computer Science 2025-09-25 Yifu Luo , Yongzhe Chang , Xueqian Wang

We present two novel generative geometric deep learning frameworks, termed Flow Matching PointNet and Diffusion PointNet, for predicting fluid flow variables on irregular geometries by incorporating PointNet into flow matching and diffusion…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Ali Kashefi

Diffusion and flow models have become the dominant paradigm for generative modeling on Riemannian manifolds, with successful applications in protein backbone generation and DNA sequence design. However, these methods require tens to…

Machine Learning · Computer Science 2026-05-04 Dongyeop Woo , Marta Skreta , Seonghyun Park , Kirill Neklyudov , Sungsoo Ahn

The goal of robust reinforcement learning (RL) is to learn a policy that is robust against the uncertainty in model parameters. Parameter uncertainty commonly occurs in many real-world RL applications due to simulator modeling errors,…

Machine Learning · Computer Science 2022-10-19 Kishan Panaganti , Zaiyan Xu , Dileep Kalathil , Mohammad Ghavamzadeh

Dense image correspondence is central to many applications, such as visual odometry, 3D reconstruction, object association, and re-identification. Historically, dense correspondence has been tackled separately for wide-baseline scenarios…

Computer Vision and Pattern Recognition · Computer Science 2026-02-11 Yuchen Zhang , Nikhil Keetha , Chenwei Lyu , Bhuvan Jhamb , Yutian Chen , Yuheng Qiu , Jay Karhade , Shreyas Jha , Yaoyu Hu , Deva Ramanan , Sebastian Scherer , Wenshan Wang

Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards successfully aligns the model with the targeted reward. However, it…

Machine Learning · Computer Science 2026-01-06 Yiyang Wang , Xi Chen , Xiaogang Xu , Yu Liu , Hengshuang Zhao

Flow matching casts sample generation as learning a continuous-time velocity field that transports noise to data. Existing flow matching networks typically predict each point's velocity independently, considering only its location and time…

Machine Learning · Computer Science 2025-11-11 Md Shahriar Rahim Siddiqui , Moshe Eliasof , Eldad Haber

Taming the generation outcome of state of the art Diffusion and Flow-Matching (FM) models without having to re-train a task-specific model unlocks a powerful tool for solving inverse problems, conditional generation, and controlled…

Machine Learning · Computer Science 2024-07-23 Heli Ben-Hamu , Omri Puny , Itai Gat , Brian Karrer , Uriel Singer , Yaron Lipman

Diffusion models create data from noise by inverting the forward paths of data towards noise and have emerged as a powerful generative modeling technique for high-dimensional, perceptual data such as images and videos. Rectified flow is a…

Diffusion models surpass previous generative models in sample quality and training stability. Recent works have shown the advantages of diffusion models in improving reinforcement learning (RL) solutions. This survey aims to provide an…

Machine Learning · Computer Science 2024-02-26 Zhengbang Zhu , Hanye Zhao , Haoran He , Yichao Zhong , Shenyu Zhang , Haoquan Guo , Tingting Chen , Weinan Zhang

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

Diffusion models have achieved significant progress in both image and video generation while still suffering from huge computation costs. As an effective solution, flow matching aims to reflow the diffusion process of diffusion models into…

Graphics · Computer Science 2025-03-13 Lei Ke , Haohang Xu , Xuefei Ning , Yu Li , Jiajun Li , Haoling Li , Yuxuan Lin , Dongsheng Jiang , Yujiu Yang , Linfeng Zhang

Diffusion models are often introduced from multiple perspectives, such as VAEs, score matching, or flow matching, accompanied by dense and technically demanding mathematics that can be difficult for beginners to grasp. One classic question…

Machine Learning · Computer Science 2026-04-14 Candi Zheng , Yuan Lan

Generating physically realistic 3D molecular structures remains a core challenge in molecular generative modeling. While diffusion models equipped with equivariant neural networks have made progress in capturing molecular geometries, they…

Machine Learning · Computer Science 2025-08-25 Zhijian Zhou , Junyi An , Zongkai Liu , Yunfei Shi , Xuan Zhang , Fenglei Cao , Chao Qu , Yuan Qi

Offline reinforcement learning (RL) can learn optimal policies from pre-collected offline datasets without interacting with the environment, but the sampled actions of the agent cannot often cover the action distribution under a given…

Machine Learning · Computer Science 2024-06-14 Xuemin Hu , Shen Li , Yingfen Xu , Bo Tang , Long Chen

Sampling from unnormalized target distributions, e.g.\ Boltzmann distributions $\mu_{\text{target}}(x) \propto \exp(-E(x)/T)$, is fundamental to many scientific applications yet computationally challenging due to complex, high-dimensional…

Machine Learning · Statistics 2026-04-22 Niclas Dern , Lennart Redl , Sebastian Pfister , Marcel Kollovieh , David Lüdke , Stephan Günnemann

We study the problem of training neural stochastic differential equations, or diffusion models, to sample from a Boltzmann distribution without access to target samples. Existing methods for training such models enforce time-reversal of the…

Machine Learning · Computer Science 2026-02-05 Julius Berner , Lorenz Richter , Marcin Sendera , Jarrid Rector-Brooks , Nikolay Malkin

Despite tremendous recent progress, Flow Matching methods still suffer from exposure bias due to discrepancies in training and inference. This paper investigates the root causes of exposure bias in Flow Matching, including: (1) the model…

Computer Vision and Pattern Recognition · Computer Science 2026-02-09 Guanbo Huang , Jingjia Mao , Fanding Huang , Fengkai Liu , Xiangyang Luo , Yaoyuan Liang , Jiasheng Lu , Xiaoe Wang , Pei Liu , Ruiliu Fu , Shao-Lun Huang

Recent developments in offline reinforcement learning have uncovered the immense potential of diffusion modeling, which excels at representing heterogeneous behavior policies. However, sampling from diffusion policies is considerably slow…

Machine Learning · Computer Science 2024-03-18 Huayu Chen , Cheng Lu , Zhengyi Wang , Hang Su , Jun Zhu