Yikun Wang

large language model (2) preference learning (1) response generation (1) multimodal learning (1) visual reasoning (1) language model alignment (1) label smoothing (1) instruction tuning (1) tree search (1) vision-language model (1) supervised fine-tuning (1) large vision-language model (1) spatial reasoning (1) multimodal reasoning (1) uncertainty-aware learning (1) preference datum (1) sample uncertainty (1) slow thinking (1) ranking metric (1) uncertainty quantification (1)