SHIZHE DIAO

large language model (11) multimodal learning (4) domain adaptation (4) n-gram representation (3) pre-trained language model (3) reasoning chain (2) reinforcement learning (2) chain-of-thought prompting (2) transfer learning (2) parameter-efficient fine-tuning (2) vision-language pre-training (2) continued pretraining (2) text encoder (2) uncertainty quantification (2) prompt engineering (2) benchmark evaluation (2) model compression (2) chain-of-thought reasoning (2) reinforcement learning from human feedback (2) instruction tuning (2)