Chunyu Wang

Pref-GRPO: Pairwise Preference Reward-based GRPO for Stable Text-to-Image Reinforcement Learning

InstantCharacter: Personalize Any Characters with a Scalable Diffusion Transformer Framework

Arbitrary Generative Video Interpolation

Directly Aligning the Full Diffusion Trajectory with Semantic Relative Preference Optimization

Unified Multimodal Chain-of-Thought Reward Model through Reinforcement Fine-Tuning