AI.info

Lifeng Shang

Explore Lifeng Shang on AI.info.

• InfMem: Learning System-2 Memory Control for Long-Context Agent
• From Verifiable Dot to Reward Chain: Harnessing Verifiable Reference-based Rewards for Reinforcement Learning of Open-ended Generation
• Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
• Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning