Zhaoye Fei

vision-language model (2) preference learning (1) mixture of expert (1) language model training (1) multimodal learning (1) text representation (1) visual reasoning (1) natural language understanding (1) semantic alignment (1) model alignment (1) action selection (1) generative model (1) tree search (1) vision language model (1) preference optimization (1) hierarchical learning (1) world model (1) embodied agent (1) overfitting mitigation (1) multi-task learning (1)