CapField-OPD: Learning Continuous Capability Fields via Joint-Anchored Multi-Teacher On-Policy Distillation for Flow Models

arXiv:2609.34658 · cs.CV · Submitted 2026-09-28 · Read on arXiv

cs.CV

Submitted: 2026-09-28

Updated: 2026-09-29

Code: https://github.com/black-forest-labs/flux

Terminology

• Distillation — 23× in this paper · explained in 2 episodes
• GRPO — 13× in this paper · explained in 6 episodes
• On-Policy Distillation — 13× in this paper · explained in 3 episodes
• Test-time Scaling — 9× in this paper · explained in 2 episodes
• Alignment — 7× in this paper · explained in 1 episode
• Flow Matching — 6× in this paper · explained in 7 episodes
• Calibration — 5× in this paper · explained in 7 episodes
• Diffusion Model — 5× in this paper · explained in 8 episodes
• Diffusion Models — 4× in this paper · explained in 6 episodes
• Reinforcement Learning — 4× in this paper · explained in 4 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Conference on Computer Vision and Pattern Recognition — 3× in this paper
• Fidelity — 3× in this paper · explained in 2 episodes
• Robustness — 3× in this paper · explained in 5 episodes
• Transformer — 3× in this paper · explained in 2 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• CVF International Conference on Computer Vision — 2× in this paper
• Distribution Matching — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Generative Models — 2× in this paper · explained in 2 episodes
• Rectified Flow — 2× in this paper · explained in 3 episodes
• Reward Function — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Ablation Studies — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Aggregation — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Consistency Distillation — 1× in this paper · explained in 2 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Entanglement — 1× in this paper · explained in 3 episodes
• Exposure Bias — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Generative Modeling — 1× in this paper · explained in 3 episodes
• Markov Decision Process (MDP) — 1× in this paper · explained in 11 episodes
• Reward Hacking — 1× in this paper · explained in 8 episodes

Sources

• Training Diffusion Models with Reinforcement Learning
• TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows
• Flow-OPD: On-Policy Distillation for Flow Matching Models
• Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
• Rethinking Classifier-Free Guidance in On-Policy Diffusion Distillation
• TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment
• MixGRPO: Unlocking Flow-based GRPO Efficiency with Mixed ODE-SDE
• DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
• DreOPD: Degraded-Reference Extrapolative On-Policy Distillation for Flow-matching Models
• Pave-GRPO: Beyond Instantaneous Guidance through Principled Average Velocity Decomposition
• Flow Matching for Generative Modeling
• Flow-GRPO: Training Flow Matching Models via Online RL
• Improving Video Generation with Human Feedback
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
• Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
• PromptRL: Prompt Matters in RL for Flow-Based Image Generation
• Qwen-Image Technical Report
• Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
• Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models

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