Directly Aligning the Full Diffusion Trajectory with Fine-Grained Human Preference Paper • 2509.06942 • Published Sep 8 • 16
Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning Paper • 2508.20751 • Published Aug 28 • 89
Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning Paper • 2505.03318 • Published May 6 • 93