Minzheng Wang

large language model (5) context window (2) multimodal large language model (2) benchmark evaluation (2) prompt optimization (2) code completion (1) language model evaluation (1) policy optimization (1) dialogue generation (1) model evaluation (1) imitation learning (1) visual reasoning (1) instruction following (1) low-resource learning (1) retrieval-augmented generation (1) in-context learning (1) data augmentation (1) multi-task learning (1) dialogue system (1) reinforcement learning (1)