DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Models

arXiv:2610.12572 · cs.LG · Submitted 2026-10-08 · Read on arXiv

cs.LG

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/vanzll/DiffusionART

Project page: https://vanzll.github.io/diffusionart-project/ABSTRACT

Terminology

• Diffusion Model — 1× in this paper · explained in 9 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes

Sources

• Flow Matching for Generative Modeling
• Qwen-Image-2.0-RL Technical Report
• Seedance 1.0: Exploring the Boundaries of Video Generation Models
• ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation
• Diffusion Model Alignment Using Direct Preference Optimization
• Flow-GRPO: Training Flow Matching Models via Online RL
• DiffusionNFT: Online Diffusion Reinforcement with Forward Process
• Training Diffusion Models with Reinforcement Learning
• DanceGRPO: Unleashing GRPO on Visual Generation
• TempFlow-GRPO: When Timing Matters for GRPO in Flow Models
• Designing Reinforcement Learning for Diffusion Models: A Unified Path-Space View
• Diffusion Reinforcement Learning via Centered Reward Distillation
• Advantage Weighted Matching: Aligning RL with Pretraining in Diffusion Models
• Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
• Tilt Matching for Scalable Sampling and Fine-Tuning
• Proximal Policy Optimization Algorithms
• Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching Models
• Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation
• Coefficients-Preserving Sampling for Reinforcement Learning with Flow Matching
• LoRA: Low-Rank Adaptation of Large Language Models

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks