UC San Diego

Large language models (LLMs) and vision language models (VLMs) are changing the world and gradually presenting human-level intelligence in various real-world scenarios, including knowledge-based question answering, mathematics, and programming. During the master period, my research focuses on understanding and improving current large language models’ reasoning capacity towards general problems solving, and efficient methods to enable the knowledge transfer for vision-language models: distill knowledge from large vision-language models.