FlowMap-OPD: Rollout--Kernel Separation for On-Policy Distillation of Few-Step Flow-Map Generators

arXiv:2609.37851 · cs.CV, cs.LG · Submitted 2026-09-29 · Read on arXiv

cs.CV, cs.LG

Submitted: 2026-09-29

Updated: 2026-09-29

Code: https://github.com/ZhiqiLi-CG/Flowmap_OPD_source

Project page: https://zhiqili-cg.github.io/Flowmap_OPD_project

Terminology

• Consistency — 106× in this paper · explained in 3 episodes
• Distillation — 34× in this paper · explained in 2 episodes
• GRPO — 22× in this paper · explained in 6 episodes
• On-Policy Distillation — 11× in this paper · explained in 3 episodes
• Cosine Similarity — 7× in this paper · explained in 3 episodes
• Distribution Matching — 5× in this paper · explained in 2 episodes
• Flow Matching — 4× in this paper · explained in 8 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Generative Modeling — 3× in this paper · explained in 3 episodes
• Adaptive Weighting — 2× in this paper · explained in 1 episode
• Benchmark — 2× in this paper · explained in 2 episodes
• Credit assignment — 2× in this paper · explained in 3 episodes
• Diffusion Model — 2× in this paper · explained in 8 episodes
• Diffusion Models — 2× in this paper · explained in 6 episodes
• Self-consistency — 2× in this paper · explained in 2 episodes
• Wasserstein Distance — 2× in this paper · explained in 4 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Additivity — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Flow Matching Model — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Generative Models — 1× in this paper · explained in 2 episodes
• Knowledge Distillation — 1× in this paper · explained in 11 episodes
• Rectified Flow — 1× in this paper · explained in 3 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Stochastic Dynamics — 1× in this paper · explained in 2 episodes

Sources

• On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
• Flow map matching with stochastic interpolants: A mathematical framework for consistency models
• Distilling Policy Distillation
• Flow-OPD: On-Policy Distillation for Flow Matching Models
• Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
• Mean Flows for One-step Generative Modeling
• GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment
• MiniLLM: On-Policy Distillation of Large Language Models
• MeanFlowNFT: Bringing Forward-Process RL to Average-Velocity Generators
• Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
• DistiLLM: Towards Streamlined Distillation for Large Language Models
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
• Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition
• Flow Matching for Generative Modeling
• Align Your Flow: Scaling Continuous-Time Flow Map Distillation
• Score-Based Generative Modeling through Stochastic Differential Equations
• Consistency Models
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models