Dongfu Jiang

large language model (3) vision-language model (2) human preference (2) benchmark evaluation (2) model evaluation (1) text generation (1) ensemble learning (1) code generation (1) preference learning (1) image editing (1) visual reasoning (1) text-to-image generation (1) multimodal interaction (1) reinforcement learning from human feedback (1) bradley-terry model (1) multimodal learning (1) pairwise ranking (1) preference modeling (1) human feedback (1) elo rating (1)