Minpeng Liao

large language model (6) mathematical reasoning (4) speech translation (4) reinforcement learning (3) knowledge distillation (2) value model (2) automatic speech recognition (2) monte carlo tree search (2) model distillation (1) cross-modal learning (1) multi-task learning (1) multimodal learning (1) continued pretraining (1) adaptive inference (1) reward hacking (1) preference optimization (1) distribution shift (1) language model reasoning (1) monte carlo sampling (1) learning to rank (1)