Hanyin Wang

clinical note generation (2) reward modeling (1) transfer learning (1) domain adaptation (1) knowledge distillation (1) policy learning (1) reinforcement learning from human feedback (1) domain expertise (1) large language model (1) process-supervised reward model (1) step-level verification (1) best-of-n selection (1) patient outcome (1) step-level reward signal (1) deep reinforcement learning (1) healthcare resource allocation (1)