Hardy Chen

chain-of-thought reasoning (2) reward modeling (1) policy optimization (1) multimodal learning (1) reinforcement learning from human feedback (1) pairwise comparison (1) vision-language model (1) supervised fine-tuning (1) multimodal large language model (1) multimodal reasoning (1) process reward (1) interactive reasoning (1) visual language model (1) process reward model (1) large language model (1) vision-language benchmark (1) human evaluation agreement (1) output reward model (1) benchmark evaluation (1) step-wise feedback (1)