Hu, Xinting
15 publications
ICLR
2026
Easier Painting than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
ICLR
2026
On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
CVPR
2025
PersonaHOI: Effortlessly Improving Face Personalization in Human-Object Interaction Generation