English
Related papers

Related papers: Flow-OPD: On-Policy Distillation for Flow Matching…

200 papers

Vision-Language-Action (VLA) models such as OpenVLA, Octo, and $\pi_0$ have shown strong generalization by leveraging large-scale demonstrations, yet their performance is still fundamentally constrained by the quality and coverage of…

Machine Learning · Computer Science 2025-10-14 Mingyang Lyu , Yinqian Sun , Erliang Lin , Huangrui Li , Ruolin Chen , Feifei Zhao , Yi Zeng

Reinforcement learning (RL) has emerged as a central paradigm for post-training LLM agents, yet its trajectory-level reward signal provides only coarse supervision for long-horizon interaction. On-Policy Self-Distillation (OPSD) complements…

Machine Learning · Computer Science 2026-05-15 Zhengxi Lu , Zhiyuan Yao , Zhuowen Han , Zi-Han Wang , Jinyang Wu , Qi Gu , Xunliang Cai , Weiming Lu , Jun Xiao , Yueting Zhuang , Yongliang Shen

We present \textbf{FlowRL}, a novel framework for online reinforcement learning that integrates flow-based policy representation with Wasserstein-2-regularized optimization. We argue that in addition to training signals, enhancing the…

Machine Learning · Computer Science 2025-06-17 Lei Lv , Yunfei Li , Yu Luo , Fuchun Sun , Tao Kong , Jiafeng Xu , Xiao Ma

Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in few step text to image generators. However, existing RL based approaches for flow matching…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Zhixiong Yue , Zixuan Ni , Feiyang Ye , Jinshan Zhang , Sheng Shen , Zhenpeng Mi

We propose ReinFlow, a simple yet effective online reinforcement learning (RL) framework that fine-tunes a family of flow matching policies for continuous robotic control. Derived from rigorous RL theory, ReinFlow injects learnable noise…

Robotics · Computer Science 2026-01-09 Tonghe Zhang , Chao Yu , Sichang Su , Yu Wang

Large language models trained with reinforcement learning (RL) for mathematical reasoning face a fundamental challenge: on problems the model cannot solve at all - "cliff" prompts - the RL gradient vanishes entirely, preventing any learning…

Machine Learning · Computer Science 2026-03-26 Ken Ding

Policy Distillation (PD) has become an effective method to improve deep reinforcement learning tasks. The core idea of PD is to distill policy knowledge from a teacher agent to a student agent. However, the teacher-student framework…

Machine Learning · Computer Science 2024-06-11 Xinqiang Yu , Chuanguang Yang , Chengqing Yu , Libo Huang , Zhulin An , Yongjun Xu

Diffusion models achieve high-quality image generation but are limited by slow iterative sampling. Distillation methods alleviate this by enabling one- or few-step generation. Flow matching, originally introduced as a distinct framework,…

Computer Vision and Pattern Recognition · Computer Science 2025-12-04 Mingyuan Zhou , Yi Gu , Huangjie Zheng , Liangchen Song , Guande He , Yizhe Zhang , Wenze Hu , Yinfei Yang

Training-time privileged information (PI) can enable language models to succeed on tasks they would otherwise fail, making it a powerful tool for reinforcement learning in hard, long-horizon settings. However, transferring capabilities…

Machine Learning · Computer Science 2026-02-17 Emiliano Penaloza , Dheeraj Vattikonda , Nicolas Gontier , Alexandre Lacoste , Laurent Charlin , Massimo Caccia

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on external models, which require separate training, operate on misaligned objectives, and exhibit…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Hila Chefer , Patrick Esser , Dominik Lorenz , Dustin Podell , Vikash Raja , Vinh Tong , Antonio Torralba , Robin Rombach

Generative policies based on diffusion models and flow matching have shown strong promise for offline reinforcement learning (RL), but their applicability remains largely confined to continuous action spaces. To address a broader range of…

Machine Learning · Computer Science 2026-05-14 Fairoz Nower Khan , Nabuat Zaman Nahim , Ruiquan Huang , Haibo Yang , Peizhong Ju

Flow matching is a recent framework to train generative models that exhibits impressive empirical performance while being relatively easier to train compared with diffusion-based models. Despite its advantageous properties, prior methods…

Computer Vision and Pattern Recognition · Computer Science 2023-07-18 Quan Dao , Hao Phung , Binh Nguyen , Anh Tran

Recent progress in large-scale flow and diffusion models raised two fundamental algorithmic challenges: (i) control-based reward adaptation of pre-trained flows, and (ii) integration of multiple models, i.e., flow merging. While current…

Machine Learning · Computer Science 2026-02-10 Riccardo De Santi , Malte Franke , Ya-Ping Hsieh , Andreas Krause

On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged context. We find that when this guidance spans the full response, all-token KL spends…

Artificial Intelligence · Computer Science 2026-05-12 Jiaxuan Wang , Xuan Ouyang , Zhiyu Chen , Yulan Hu , Zheng Pan , Xin Li , Lan-Zhe Guo

Diffusion models have revolutionized generative tasks through high-fidelity outputs, yet flow matching (FM) offers faster inference and empirical performance gains. However, current foundation FM models are computationally prohibitive for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-04 Johannes Schusterbauer , Ming Gui , Frank Fundel , Björn Ommer

Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (RL). We show that the prevailing paradigms, off-policy distillation and on-policy…

Machine Learning · Computer Science 2026-05-19 Anhao Zhao , Haoran Xin , Yingqi Fan , Junlong Tong , Wenjie Li , Xiaoyu Shen

Recent progress in flow-based generative models and reinforcement learning (RL) has improved text-image alignment and visual quality. However, current RL training for flow models still has two main problems: (i) GRPO-style fixed per-prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-01-13 Kaijie Chen , Zhiyang Xu , Ying Shen , Zihao Lin , Yuguang Yao , Lifu Huang

A key challenge in music generation models is their lack of direct alignment with human preferences, as music evaluation is inherently subjective and varies widely across individuals. We introduce MR-FlowDPO, a novel approach that enhances…

Sound · Computer Science 2025-12-16 Alon Ziv , Sanyuan Chen , Andros Tjandra , Yossi Adi , Wei-Ning Hsu , Bowen Shi

Discrete diffusion models excel at visual synthesis but rely on slow, iterative decoding. Existing single-step distillation methods attempt to bypass this bottleneck, either by training auxiliary score networks that effectively double…

Computer Vision and Pattern Recognition · Computer Science 2026-05-21 Chaoyang Wang , Yunhai Tong

We study {on-policy self-distillation} (OPSD), where a language model improves its reasoning ability by distilling privileged teacher distributions along its own on-policy trajectories. Despite the performance gains of OPSD, we identify a…

Machine Learning · Computer Science 2026-05-13 Yuxiao Yang , Xiaoyun Wang , Weitong Zhang
‹ Prev 1 4 5 6 7 8 10 Next ›