My research centers on Natural Language Processing, Machine Learning and Artificial Intelligence, with a keen interest in developing efficient models and benchmarks to foster machine intelligence at a human level. My research aims to continually acquire precise knowledge from the ever-changing, open world through large-scale weak supervision, endow machines with generalizable, robust and efficient intelligence, and significantly enhance human experience when interacting with the technologies. My recent research interests are the fundamentals, understanding, enhancing, and forward-looking of Large Language Models (LLMs) and Vision-Language Models (VLMs), with broad downstream applications in NLP and Multimodal domains.