Yunxuan Li

large language model (3) few-shot learning (1) uncertainty quantification (1) visual question answering (1) sequential decision making (1) direct preference optimization (1) preference alignment (1) multimodal learning (1) visual localization (1) gaussian splatting (1) embodied ai (1) question generation (1) reinforcement learning from human feedback (1) geometric prior (1) multi-objective optimization (1) language model (1) policy training (1) novel view synthesis (1) model scaling (1) process supervision (1)