Wenbo Su

large language model (14) benchmark evaluation (4) factuality evaluation (3) chinese language (3) question answering (3) reinforcement learning (2) reward modeling (2) fine-grained evaluation (2) critic model (2) long-context processing (2) multi-turn dialogue (2) domain adaptation (2) instruction following (2) scaling law (2) knowledge distillation (1) direct preference optimization (1) preference learning (1) mathematical reasoning (1) transfer learning (1) visual question answering (1)