Daojing He

large language model (5) model compression (3) transfer learning (2) multimodal large language model (2) model merging (2) adversarial attack (2) safety alignment (2) jailbreak attack (2) vision-language alignment (1) question answering (1) domain generalization (1) multimodal learning (1) multi-task learning (1) code generation (1) knowledge editing (1) fact verification (1) model security (1) model editing (1) neural network optimization (1) knowledge unlearning (1)