AI.info

Bo An

Explore Bo An on AI.info.

• Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation
• Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs
• Harnessing Reasoning Trajectories for Hallucination Detection via Answer-agreement Representation Shaping
• Failure-Aware RL: Reliable Offline-to-Online Reinforcement Learning with Self-Recovery for Real-World Manipulation
• AgentOCR: Reimagining Agent History via Optical Self-Compression
• Training Diffusion Policies via Prior-Mapping Co-Evolution
• Empirical Study on Robustness and Resilience in Cooperative Multi-Agent Reinforcement Learning