The recent advancements in large foundation models have revolutionized the way humans interact with AI. This project aims to delve into the application and enhancement of reasoning capabilities in these models across a range of downstream scenarios, such as E-Commerce (Amazon), Social Media (Twitter), and solving generalizable commonsense problems. Our investigation will encompass both large language models (LLM) and large vision-language models (LVLM). This project is highly research-oriented, and it requires applicants to possess strong self-motivation and determination.