Hepeng Wang

large language model (2) reinforcement learning (2) knowledge transfer (1) in-context learning (1) graph representation (1) instruction tuning (1) gradient-based method (1) autonomous learning (1) lifelong learning (1) multi-objective optimization (1) data selection (1) supervised fine-tuning (1) experience transfer (1) experiential learning (1) task categorization (1) reward optimization (1) agent alignment (1) gradient concentration (1) question categorization (1) meta learning (1)