JinJin Li

model compression (1) binary classification (1) visual question answering (1) direct preference optimization (1) in-context learning (1) reinforcement learning from human feedback (1) vision language model (1) node classification (1) vision-language model (1) supervised fine-tuning (1) multimodal large language model (1) mixed-precision quantization (1) inference speed (1) rejection sampling (1) correlation matrix (1) housing prediction (1) large language model alignment (1) factor model (1) image-text relevancy (1) large language model (1)