AI.info

Yongbin Li

Explore Yongbin Li on AI.info.

• P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
• ExpSeek: Self-Triggered Experience Seeking for Web Agents
• Reward Modeling from Natural Language Human Feedback
• Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions
• Understanding Generalization in Role-Playing Models via Information Theory
• Saber: An Efficient Sampling with Adaptive Acceleration and Backtracking Enhanced Remasking for Diffusion Language Model