I am passionate about developing Machine Learning (ML) and Large Language Model (LLM) applications, with the goal of creating impactful and powerful solutions.
Beyond this, I am also an enthusiastic open-source contributor, currently contributing to Flyte, a flexible and scalable workflow orchestration platform.
My name is Vincent. I am a master student at UC San Diego. I majored in Computer Science with a focus on Natural Language Processing (NLP) and research related to Large Language Models (LLMs).
Having grown up in the countryside, I became acutely aware of the disparity in resources between rural and urban areas. Witnessing the remarkable potential of LLMs and NLP, I am deeply passionate about developing LLM applications that can benefit humanity.
I am interested in creating LLM applications for education and healthcare purposes.
Having over 2 years of research experience on NLP/CV, accompanied by industrial experience on LLM application development and integration.
A meal planning web app built with Next.js, MongoDB, and Google OAuth. FoodiePlan leverages Gemini AI to generate personalized recipe suggestions and weekly meal plans based on user preferences, dietary restrictions, and available ingredients.
Case Study
A lecture abstract-based question generation system optimizing the preparation process for educators in academic lectures and associated Q&A sessions. Given a lecture abstract, E-QGen generates potential student inquiries. The questions suggested by our system are expected to not only facilitate teachers in preparing answers in advance but also enable them to supply additional resources when necessary. This demo paper was accepted by the International Joint Conference on Artificial Intelligence (IJCAI) 2024 at Jeju.
Paper Link
Collaborating with open-source community members worldwide to implement features and fix bugs strengthened my software development and communication skills, laying the foundation for contributing to large-scale projects. My contributions mainly focus on enhancing dataclass support and implementing features that strengthen the usability of Flyte and its python SDK Flytekit. Since now, I have contributed over 15 pull requests and 1000 lines of code.
Case Study