Xian Gao

image classification (1) benchmark evaluation (1) reward modeling (1) few-shot learning (1) binary classification (1) human perception (1) question answering (1) multimodal learning (1) adversarial attack (1) deep neural network (1) reward model (1) vision-language model (1) multimodal large language model (1) evaluation benchmark (1) parameter-efficient tuning (1) overfitting mitigation (1) adversarial example (1) multimodal reasoning (1) process reward (1) multilingual evaluation (1)