Xufang Luo

sample efficiency (3) deep reinforcement learning (3) offline reinforcement learning (3) long context (2) reinforcement learning (2) representation learning (2) prompt compression (2) position bia (2) large language model (2) direct preference optimization (1) function approximation (1) policy gradient (1) contrastive learning (1) preference alignment (1) sequence generation (1) visual perception (1) visual reasoning (1) transfer learning (1) trajectory modeling (1) policy learning (1)