Renjie Luo

large language model (2) benchmark evaluation (1) model evaluation (1) language model evaluation (1) large multimodal model (1) supervised fine-tuning (1) inference acceleration (1) multimodal reasoning (1) artificial general intelligence (1) error accumulation (1) step-by-step reasoning (1) small language model (1) scientific reasoning (1) reasoning training (1) model benchmark (1) long chain-of-thought training (1) reinforcement learning (1) metric computation (1)