English
Related papers

Related papers: DeFlow: Decoupling Manifold Modeling and Value Max…

200 papers

Accurate polyp segmentation remains challenging due to irregular lesion morphologies, ambiguous boundaries, and heterogeneous imaging conditions. While U-Net variants excel at local feature fusion, they often lack explicit mechanisms to…

Image and Video Processing · Electrical Eng. & Systems 2025-02-27 Pu Wang , Huaizhi Ma , Zhihua Zhang , Zhuoran Zheng

Incorporating pre-collected offline data can substantially improve the sample efficiency of reinforcement learning (RL), but its benefits can break down when the transition dynamics in the offline dataset differ from those encountered…

Machine Learning · Computer Science 2026-01-22 Lingkai Kong , Haichuan Wang , Tonghan Wang , Guojun Xiong , Milind Tambe

The multi-step denoising process in diffusion and Flow Matching models causes major efficiency issues, which motivates research on few-step generation. We present Solution Flow Models (SoFlow), a framework for one-step generation from…

Machine Learning · Computer Science 2026-03-03 Tianze Luo , Haotian Yuan , Zhuang Liu

Rectified flow models have become a de facto standard in image generation due to their stable sampling trajectories and high-fidelity outputs. Despite their strong generative capabilities, they face critical limitations in image editing…

Computer Vision and Pattern Recognition · Computer Science 2025-10-31 Sung-Hoon Yoon , Minghan Li , Gaspard Beaudouin , Congcong Wen , Muhammad Rafay Azhar , Mengyu Wang

Reparameterization Policy Gradient (RPG) has emerged as a powerful paradigm for model-based reinforcement learning, enabling high sample efficiency by backpropagating gradients through differentiable dynamics. However, prior RPG approaches…

Machine Learning · Computer Science 2026-02-04 Hai Zhong , Zhuoran Li , Xun Wang , Longbo Huang

Generative models, especially diffusion and flow-based models, have been promising in offline multi-agent reinforcement learning. However, integrating powerful generative models into this framework poses unique challenges. In particular,…

Machine Learning · Computer Science 2026-03-02 Zhuoran Li , Xun Wang , Hai Zhong , Qingxin Xia , Lihua Zhang , Longbo Huang

Offline reinforcement learning (RL) aims to learn the optimal policy from a fixed dataset generated by behavior policies without additional environment interactions. One common challenge that arises in this setting is the…

Machine Learning · Computer Science 2026-02-06 Songyuan Zhang , Oswin So , H. M. Sabbir Ahmad , Eric Yang Yu , Matthew Cleaveland , Mitchell Black , Chuchu Fan

Multiple federated learning (FL) methods are proposed for traffic flow forecasting (TFF) to avoid heavy-transmission and privacy-leaking concerns resulting from the disclosure of raw data in centralized methods. However, these FL methods…

Machine Learning · Computer Science 2024-11-22 Qingxiang Liu , Sheng Sun , Yuxuan Liang , Xiaolong Xu , Min Liu , Muhammad Bilal , Yuwei Wang , Xujing Li , Yu Zheng

Flow matching has emerged as a simulation-free alternative to diffusion-based generative modeling, producing samples by solving an ODE whose time-dependent velocity field is learned along an interpolation between a simple source…

Machine Learning · Statistics 2026-04-10 Shivam Kumar , Yixin Wang , Lizhen Lin

Balancing policy expressiveness with the exploration-exploitation trade-off is a core challenge in online Reinforcement Learning (RL). While Stochastic Differential Equation (SDE)-based diffusion policies can represent complex, multimodal…

Machine Learning · Computer Science 2026-05-27 Ting Gao , Stavros Orfanoudakis , Nan Lin , Winnie Daamen , Serge Hoogendoorn , Elvin Isufi

Diffusion models have recently emerged as expressive policy representations for online reinforcement learning (RL). However, their iterative generative processes introduce substantial training and inference overhead. To overcome this…

Machine Learning · Computer Science 2026-04-17 Xiaoyi Dong , Xi Sheryl Zhang , Jian Cheng

Expressive policies based on flow-matching have been successfully applied in reinforcement learning (RL) more recently due to their ability to model complex action distributions from offline data. These algorithms build on standard policy…

Machine Learning · Computer Science 2026-02-04 Mingxuan Li , Junzhe Zhang , Elias Bareinboim

Scene flow estimation determines a scene's 3D motion field, by predicting the motion of points in the scene, especially for aiding tasks in autonomous driving. Many networks with large-scale point clouds as input use voxelization to create…

Computer Vision and Pattern Recognition · Computer Science 2024-01-30 Qingwen Zhang , Yi Yang , Heng Fang , Ruoyu Geng , Patric Jensfelt

The difficulty of obtaining paired data remains a major bottleneck for learning image restoration and enhancement models for real-world applications. Current strategies aim to synthesize realistic training data by modeling noise and…

Computer Vision and Pattern Recognition · Computer Science 2021-09-17 Valentin Wolf , Andreas Lugmayr , Martin Danelljan , Luc Van Gool , Radu Timofte

Flow based generative models have charted an impressive path across multiple visual generation tasks by adhering to a simple principle: learning velocity representations of a linear interpolant. However, we observe that training velocity…

Computer Vision and Pattern Recognition · Computer Science 2025-09-04 Inkyu Shin , Chenglin Yang , Liang-Chieh Chen

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative…

Machine Learning · Computer Science 2025-10-20 Mingyang Sun , Pengxiang Ding , Weinan Zhang , Donglin Wang

In recent years, generative models have shown remarkable capabilities across diverse fields, including images, videos, language, and decision-making. By applying powerful generative models such as flow-based models to reinforcement…

Machine Learning · Computer Science 2025-05-28 Jifeng Hu , Sili Huang , Siyuan Guo , Zhaogeng Liu , Li Shen , Lichao Sun , Hechang Chen , Yi Chang , Dacheng Tao

Flow-based generative models, including diffusion models, excel at modeling continuous distributions in high-dimensional spaces. In this work, we introduce Flow Policy Optimization (FPO), a simple on-policy reinforcement learning algorithm…

Machine Learning · Computer Science 2025-08-04 David McAllister , Songwei Ge , Brent Yi , Chung Min Kim , Ethan Weber , Hongsuk Choi , Haiwen Feng , Angjoo Kanazawa

The implementation of optimal power flow (OPF) methods to perform voltage and power flow regulation in electric networks is generally believed to require extensive communication. We consider distribution systems with multiple controllable…

Machine Learning · Computer Science 2019-08-15 Roel Dobbe , Oscar Sondermeijer , David Fridovich-Keil , Daniel Arnold , Duncan Callaway , Claire Tomlin

Optimal Power Flow (OPF) is a core optimization problem in power system operation and planning, aiming to minimize generation costs while satisfying physical constraints such as power flow equations, generator limits, and voltage limits.…

Machine Learning · Computer Science 2025-12-02 Xuezhi Liu