Keyi Kong

large language model (3) reinforcement learning (2) transfer learning (1) preference alignment (1) multimodal learning (1) explanation generation (1) visual reasoning (1) robust alignment (1) language model alignment (1) reinforcement learning from human feedback (1) human feedback (1) supervised fine-tuning (1) noisy label (1) noisy preference (1) perplexity correction (1) video understanding (1) fine-grained understanding (1) logic reasoning (1) human preference (1) visual question answering (1)