Alleviating Sparse Rewards by Modeling Step-Wise and Long-Term Sampling Effects in Flow-Based GRPO Paper • 2602.06422 • Published 4 days ago • 36
SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation Paper • 2507.09862 • Published Jul 14, 2025 • 51
IterComp: Iterative Composition-Aware Feedback Learning from Model Gallery for Text-to-Image Generation Paper • 2410.07171 • Published Oct 9, 2024 • 43