Hanwang Zhang

4 papers NTU

• Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
• Enhancing CLIP Robustness via Cross-Modality Alignment
• Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens
• Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning