Xidong Wang

large language model (5) multimodal large language model (3) benchmark evaluation (2) visual question answering (2) domain adaptation (1) state space model (1) zero-shot learning (1) multimodal learning (1) reward modeling (1) computational efficiency (1) entropy reduction (1) pairwise comparison (1) knowledge distillation (1) memory efficiency (1) multi-modal large language model (1) human-ai collaboration (1) medical imaging (1) controllable generation (1) zero-shot transfer (1) reinforcement learning (1)