Shenzhi Wang

large language model (3) policy constraint (2) offline reinforcement learning (2) reward model (2) agent system (2) reward modeling (1) adversarial learning (1) contrastive learning (1) direct preference optimization (1) preference learning (1) preference alignment (1) data annotation (1) efficient inference (1) deep learning (1) benchmark evaluation (1) model alignment (1) reinforcement learning from human feedback (1) feature extraction (1) early exit (1) ai safety (1)