AI.info

Xuan Zhang

Explore Xuan Zhang on AI.info.

• Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
• Multilingual Agent-Based World Modeling for Social Science
• Aligning by Misaligning: Boundary-aware Curriculum Learning for Multimodal Alignment
• Synergy over Discrepancy: A Partition-Based Approach to Multi-Domain LLM Fine-Tuning