English
Related papers

Related papers: ScoRe-Flow: Complete Distributional Control via Sc…

200 papers

Learning the inverse dynamics of soft continuum robots remains challenging due to high-dimensional nonlinearities and complex actuation coupling. Conventional feedback-based controllers often suffer from control chattering due to corrective…

Robotics · Computer Science 2026-04-06 Hang Yang , Fangju Yang , Yangming Zhang , Ibrahim Alsarraj , Yuhao Wang , Zhenye Luo , Zixi Chen , Ke Wu

Reinforcement learning (RL) has achieved significant success across a wide range of domains, however, most existing methods are formulated in discrete time. In this work, we introduce a novel RL method for continuous-time control, where…

Machine Learning · Computer Science 2025-10-21 Chengxiu Hua , Jiawen Gu , Yushun Tang

Diffusion-based generative models have achieved state-of-the-art performance for perceptual quality in speech enhancement (SE). However, their iterative nature requires numerous Neural Function Evaluations (NFEs), posing a challenge for…

Flow-matching policies have emerged as a powerful paradigm for generalist robotics. These models are trained to imitate an action chunk, conditioned on sensor observations and textual instructions. Often, training demonstrations are…

Machine Learning · Computer Science 2025-07-22 Samuel Pfrommer , Yixiao Huang , Somayeh Sojoudi

Sim-to-real transfer of locomotion policies often leads to performance degradation due to the inevitable sim-to-real gap. Naively fine-tuning these policies directly on hardware is problematic, as it poses risks of mechanical failure and…

Robotics · Computer Science 2026-03-19 Elham Daneshmand , Shafeef Omar , Glen Berseth , Majid Khadiv , Hsiu-Chin Lin

Generative policies based on diffusion and flow matching achieve strong performance in robotic manipulation by modeling multi-modal human demonstrations. However, their reliance on iterative Ordinary Differential Equation (ODE) integration…

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

Flow Matching (FM) is a simulation-free method for learning a continuous and invertible flow to interpolate between two distributions, and in particular to generate data from noise. Inspired by the variational nature of the diffusion…

Machine Learning · Statistics 2025-07-14 Chen Xu , Xiuyuan Cheng , Yao Xie

Reward-based fine-tuning steers a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the pretrained model. Although existing methods are derived from different perspectives, we show…

Machine Learning · Computer Science 2026-05-08 Jeongjae Lee , Jinho Chang , Jeongsol Kim , Jong Chul Ye

Diffusion policies are expressive yet incur high inference latency. Flow Matching (FM) enables one-step generation, but integrating it into Maximum Entropy Reinforcement Learning (MaxEnt RL) is challenging: the optimal policy is an…

Machine Learning · Computer Science 2026-02-03 Zeqiao Li , Yijing Wang , Haoyu Wang , Zheng Li , Zhiqiang Zuo

Model-free or learning-based control, in particular, reinforcement learning (RL), is expected to be applied for complex robotic tasks. Traditional RL requires a policy to be optimized is state-dependent, that means, the policy is a kind of…

Machine Learning · Computer Science 2022-08-09 Taisuke Kobayashi , Kenta Yoshizawa

Reinforcement learning (RL) in few-shot scenarios with limited sensor data is challenging due to insufficient training samples, particularly in applications like Dynamic Voltage and Frequency Scaling (DVFS) where sensor readings are…

Machine Learning · Computer Science 2026-01-13 Mohammad Pivezhandi , Abusayeed Saifullah

We propose a new reinforcement learning (RL) formulation for training continuous-time score-based diffusion models for generative AI to generate samples that maximize reward functions while keeping the generated distributions close to the…

Machine Learning · Computer Science 2025-08-12 Xuefeng Gao , Jiale Zha , Xun Yu Zhou

This paper studies satisfaction of temporal properties on unknown stochastic processes that have continuous state spaces. We show how reinforcement learning (RL) can be applied for computing policies that are finite-memory and deterministic…

Systems and Control · Electrical Eng. & Systems 2020-09-29 Milad Kazemi , Sadegh Soudjani

Prior flow matching methods in robotics have primarily learned velocity fields to morph one distribution of trajectories into another. In this work, we extend flow matching to capture second-order trajectory dynamics, incorporating…

Robotics · Computer Science 2025-03-11 Khang Nguyen , An T. Le , Tien Pham , Manfred Huber , Jan Peters , Minh Nhat Vu

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

Recent advances in diffusion$/$flow-matching policies have enabled imitation learning of complex, multi-modal action trajectories. However, they are computationally expensive because they sample a trajectory of trajectories: a…

Reinforcement learning from human feedback (RLHF), which aligns a diffusion model with input prompt, has become a crucial step in building reliable generative AI models. Most works in this area use a discrete-time formulation, which is…

Machine Learning · Computer Science 2025-08-25 Hanyang Zhao , Haoxian Chen , Ji Zhang , David D. Yao , Wenpin Tang

Reinforcement Learning (RL) of robotic manipulation skills, despite its impressive successes, stands to benefit from incorporating domain knowledge from control theory. One of the most important properties that is of interest is control…

Robotics · Computer Science 2021-03-03 Shahbaz Abdul Khader , Hang Yin , Pietro Falco , Danica Kragic

Likelihood-based policy gradient methods are the dominant approach for training robot control policies from rewards. These methods rely on differentiable action likelihoods, which constrain policy outputs to simple distributions like…