English
Related papers

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

200 papers

We present DeFlow, a decoupled offline RL framework that leverages flow matching to faithfully capture complex behavior manifolds. Optimizing generative policies is computationally prohibitive, typically necessitating backpropagation…

Machine Learning · Computer Science 2026-01-21 Zhancun Mu

Recent advances in few-step diffusion distillation have enabled efficient image generation, yet aligning these models with human preferences remains challenging. We propose Reward-Tilted Distribution Matching Distillation (RTDMD), a…

Computer Vision and Pattern Recognition · Computer Science 2026-05-29 Yushi Huang , Xiangxin Zhou , Ruoyu Wang , Chi Zhang , Jun Zhang , Tianyu Pang

Reinforcement learning (RL) has become a standard technique for post-training diffusion-based image synthesis models, as it enables learning from reward signals to explicitly improve desirable aspects such as image quality and prompt…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 David McAllister , Miika Aittala , Tero Karras , Janne Hellsten , Angjoo Kanazawa , Timo Aila , Samuli Laine

Recent works have shown that optical flow can be learned by deep networks from unlabelled image pairs based on brightness constancy assumption and smoothness prior. Current approaches additionally impose an augmentation regularization term…

Computer Vision and Pattern Recognition · Computer Science 2022-11-14 Lingtong Kong , Jie Yang

Flow-based generative models have shown remarkable success in text-to-image generation, yet fine-tuning them with intermediate feedback remains challenging, especially for continuous-time flow matching models. Most existing approaches…

Machine Learning · Computer Science 2025-10-22 Jiajun Fan , Chaoran Cheng , Shuaike Shen , Xiangxin Zhou , Ge Liu

On-policy self-distillation (OPSD) is an emerging LLM post-training paradigm in which the model serves as its own teacher: conditioned on privileged information such as a reference trace or hint, the same policy provides dense token-level…

Machine Learning · Computer Science 2026-05-22 Hongbin Zhang , Chaozheng Wang , Kehai Chen , Youcheng Pan , Yang Xiang , Jinpeng Wang , Min Zhang

Reinforcement learning has emerged as a promising paradigm for aligning diffusion and flow-matching models with human preferences, yet practitioners face fragmented codebases, model-specific implementations, and engineering complexity. We…

Machine Learning · Computer Science 2026-03-17 Bowen Ping , Chengyou Jia , Minnan Luo , Hangwei Qian , Ivor Tsang

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

Generative speech enhancement offers a promising alternative to traditional discriminative methods by modeling the distribution of clean speech conditioned on noisy inputs. Post-training alignment via reinforcement learning (RL) effectively…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-26 Haoxu Wang , Biao Tian , Yiheng Jiang , Zexu Pan , Shengkui Zhao , Bin Ma , Daren Chen , Xiangang Li

Face presentation attack detection (FacePAD) remains challenging under diverse spoofing representation, including 2D print and replay, 3D mask-based spoofing, makeup-induced appearance manipulation, and physical occlusions, as well as under…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Muhammad Shahid Jabbar , Muhammad Sohail Ibrahim , Taha Hasan Masood Siddique , Kejie Huang , Shujaat Khan

Recent reinforcement learning (RL) post-training approaches primarily optimize the final output policy using sparse outcome-level rewards, while largely overlooking predictive signals encoded in intermediate representations. In this paper,…

Machine Learning · Computer Science 2026-05-29 Xinyu Liu , Darryl Cherian Jacob , Yang Zhou , Jindong Wang , Pan He

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

Large language models (LLMs) are increasingly adapted to proprietary and domain-specific corpora that contain sensitive information, creating a tension between formal privacy guarantees and efficient deployment through model compression.…

Machine Learning · Computer Science 2026-04-07 Fatemeh Khadem , Sajad Mousavi , Yi Fang , Yuhong Liu

Data heterogeneity hinders clinical deployment of medical image analysis models, and generative data augmentation helps mitigate this issue. However, recent diffusion-based methods that synthesize image-mask pairs often ignore distribution…

Image and Video Processing · Electrical Eng. & Systems 2026-04-06 Jie Yang , Ziqi Ye , Aihua Ke , Jian Luo , Bo Cai , Xiaosong Wang

Diffusion models have shown great promise for image and video generation, but sampling from state-of-the-art models requires expensive numerical integration of a generative ODE. One approach for tackling this problem is rectified flows,…

Computer Vision and Pattern Recognition · Computer Science 2024-10-10 Sangyun Lee , Zinan Lin , Giulia Fanti

On-policy distillation (OPD) is widely used for LLM post-training. When pushed with a reward-extrapolation coefficient lambda > 1, the student can lift past the teacher in domain, but past a threshold lambda* the same step violates the…

Machine Learning · Computer Science 2026-05-12 Xin Li , Hao Jiang , Annan Wang , Yichi Zhang , Chau Yuen

On-policy distillation (OPD) has shown strong potential for transferring reasoning ability from frontier or domain-specific models to smaller students. While effective on static single-turn tasks, its behavior in multi-turn agent settings…

Machine Learning · Computer Science 2026-04-30 Jiaqi Wang , Wenhao Zhang , Weijie Shi , Yaliang Li , James Cheng

On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uniformity of OPD signals by prioritizing high-entropy or high-disagreement tokens. We…

Machine Learning · Computer Science 2026-05-27 Yuanyi Wang , Su Lu , Yanggan Gu , Pengkai Wang , Yifan Yang , Zhaoyi Yan , Congkai Xie , Jianmin Wu , Hongxia Yang

With the rapidly expanding landscape of large language models, aligning model generations with human values and preferences is becoming increasingly important. Popular alignment methods, such as Reinforcement Learning from Human Feedback,…

Computation and Language · Computer Science 2025-02-21 Mingye Zhu , Yi Liu , Lei Zhang , Junbo Guo , Zhendong Mao

Reinforcement learning (RL) has been widely used to train LLM agents for multi-turn interactive tasks, but its sample efficiency is severely limited by sparse rewards and long horizons. On-policy self-distillation (OPSD) alleviates this by…

Machine Learning · Computer Science 2026-04-14 Hao Wang , Guozhi Wang , Han Xiao , Yufeng Zhou , Yue Pan , Jichao Wang , Ke Xu , Yafei Wen , Xiaohu Ruan , Xiaoxin Chen , Honggang Qi