Flow-OPD: On-Policy Distillation for Flow Matching Models
University of Science and Technology of China（中国科学技术大学）；University of California, Los Angeles（加州大学洛杉矶分校）；The Chinese University of Hong Kong（香港中文大学）；Xiaohongshu Inc.（小红书公司）
Existing Flow Matching (FM) text-to-image models suffer from two critical bottlenecks under multi-task alignment: the reward sparsity induced by scalar-valued rewards, and the gradient interference arising from jointly optimizing heterogeneous objectives, which together give rise to a 'seesaw effect' of competing metrics and pervasive reward hacking. Inspired by the success of On-Policy Distillation (OPD) in the large language model community, we propose Flow-OPD, the first unified post-training framework that integrates on-policy distillation into Flow Matching models. Flow-OPD adopts a two-stage alignment strategy: it first cultivates domain-specialized teacher models via single-reward GRPO fine-tuning, allowing each expert to reach its performance ceiling in isolation; it then establishes a robust initial policy through a Flow-based Cold-Start scheme and seamlessly consolidates heterogeneous expertise into a single student via a three-step orchestration of on-policy sampling, task-routing labeling, and dense trajectory-level supervision. We further introduce Manifold Anchor Regularization (MAR), which leverages a task-agnostic teacher to provide full-data supervision that anchors generation to a high-quality manifold, effectively mitigating the aesthetic degradation commonly observed in purely RL-driven alignment. Built upon Stable Diffusion 3.5 Medium, Flow-OPD raises the GenEval score from 63 to 92 and the OCR accuracy from 59 to 94, yielding an overall improvement of roughly 10 points over vanilla GRPO, while preserving image fidelity and human-preference alignment and exhibiting an emergent 'teacher-surpassing' effect. These results establish Flow-OPD as a scalable alignment paradigm for building generalist text-to-image models. The codes and weights will be released in: https://github.com/CostaliyA/Flow-OPD .
BAS-OPD: Budget-Aware Selective On-Policy Self-Distillation for Fine-Grained Multimodal Perception
HFIPS, Chinese Academy of Sciences（中国科学院合肥物质科学研究院）；University of Science and Technology of China（中国科学技术大学）；University of California, Los Angeles（加利福尼亚大学洛杉矶分校）
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
National University of Singapore（新加坡国立大学）；Ludwig Maximilian University of Munich（慕尼黑大学）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Sun Yat-sen University（中山大学）
Learning to Revise Reasoning with Segment-wise On-Policy Distillation
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Science and Technology of China（中国科学技术大学）；Alibaba Group（阿里巴巴集团）；Stanford University（斯坦福大学）
Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?
LeapLab, Tsinghua University（清华大学LeapLab）；Qiuzhen College, Tsinghua University（清华大学求真书院）；Beihang University（北京航空航天大学）；National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong（香港中文大学）；E Fund Management Co., Ltd.（易方达基金管理有限公司）
Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation
Eastern Institute of Technology（东技术院）；The Hong Kong Polytechnic University（香港理工大学）；Shanghai Jiao Tong University（上海交通大学）；Thrust of Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（人工智能 thrust，香港科学与技术大学（广州））
FocusOPD: Structure-Guided On-Policy Distillation for Diffusion Models
University of Science and Technology of China（中国科学技术大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Rethinking On-Policy Distillation of Large Language Models II: One Training Example
University of Chinese Academy of Sciences（中国科学院大学）；Tsinghua University（清华大学）；Northeastern University（东北大学）；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Johns Hopkins University（约翰斯·霍普金斯大学）
PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation
Eastern Institute of Technology, Ningbo（宁波东方理工大学）；The Hong Kong Polytechnic University（香港理工大学）；Shanghai Jiao Tong University（上海交通大学）；University of Waterloo（滑铁卢大学）
Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes
State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA（多模态人工智能系统国家重点实验室，中科院自动化所）；School of Artificial Intelligence, UCAS（中国科学技术大学人工智能学院）；Fudan University（复旦大学）；Independent Researcher（独立研究者）
Teacher-Guided Policy Optimization for On-Policy Reasoning Distillation under Large Policy Divergence
School of Computer Science and Engineering, Northeastern University, China（东北大学计算机科学与工程学院）；Tsinghua University（清华大学）；Meituan（美团）；Meta AI；NiuTrans Research, Shenyang, China（新译研究院，沈阳，中国）
Beijing University of Posts and Telecommunications（北京邮电大学）；ByteDance（字节跳动）；USTC（中国科学技术大学）；Beijing Key Laboratory of Network System and Network Culture（北京网络系统与网络文化重点实验室）；Key Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism（文化和旅游部互动技术与体验系统重点实验室）；Zhongguancun Academy（中关村科学城）
CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models
University of Science and Technology of China（中国科学技术大学）；Shanghai Jiao Tong University（上海交通大学）；Fudan University（复旦大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
