Summary
Tanmay Gupta is a Senior Research Scientist at the Allen Institute for AI with 12 years of experience building multimodal agents, vision-language models, and LLM-guided code-use systems. He led award-winning work such as VisProg (CVPR 2023 best paper) and has contributed foundational research on general-purpose vision models, vision-language action models for robotics, and code-oriented agent tools like CodeNav and MutaGrep. A UIUC PhD advised by Derek Hoiem, Tanmay blends deep learning for vision and NLP with practical system-building, from text-to-video composition to weakly supervised grounding. Based in Seattle, he now leads PRIOR team research on web, coding, and tool-use agents, and is known for turning research prototypes into versatile, continually learning systems that make AI accessible across industries.
12 years of coding experience
11 years of employment as a software developer
Indian Institute of Technology Kanpur
Delhi Public School, Bokaro Steel City
Doctor of Philosophy (PhD) Computer Vision and Machine Learning, Doctor of Philosophy (PhD) Computer Vision and Machine Learning at University of Illinois Urbana-Champaign
English, Hindi