Xiangyang Li

5 papers University of Science and Technology of China

• MTRec: Learning to Align with User Preferences via Mental Reward Models
• MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks
• MoonCast: High-Quality Zero-Shot Podcast Generation
• Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
• Purest Quantum State Identification