Xingyu Fu is a postdoctoral researcher focused on generative multimodal models that bridge vision and language, pursuing research on emergent abilities, evaluation, and grounded perception and reasoning. With a PhD from the University of Pennsylvania under Dan Roth and mentorship earlier from Jiawei Han at UIUC, he brings eight years of research experience and internships at Microsoft and AWS AI Labs that translated academic ideas into large-scale ML practice. His work spans multimodal LLMs and text-to-image/video generation with an emphasis on robust evaluation methods to make models better at perceiving, reasoning, and reacting in real-world settings. Based in Philadelphia and soon at Princeton, he combines rigorous theory-driven research with applied experimentation—an approach hinted at by a playful GitHub bio, “May the Force be with you,” that reflects a curiosity-driven, collaborative mindset.
8 years of coding experience
1 year of employment as a software developer
University of Illinois Urbana-Champaign
Doctor of Philosophy - PhD, Computer Science, Doctor of Philosophy - PhD, Computer Science at University of Pennsylvania
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.