Hi there!

I am a fourth-year PhD student at NYU, working in embodied spatial reasoning and robot manipulation. My research focuses on adapting large-scale Vision-Language Models (VLMs) in a range of robot perception tasks such as object detection, grasping, planning, long-horizon manipulation and question answering. More recently I am working on agentic frameworks that leverage tool-calling VLMs, interfaced with Vision-Language Action (VLAs) and World Action Models (WAMs) to transform user intent specified through free-form language into low-level robot actuator commands for manipulation.

Prior to my PhD I earned my Bachelor’s degree in Physics and Master’s in Artificial Intelligence from the Indian Institute of Technology Bombay (India).

At my core, I’m a problem solver who likes to solve the toughest of problems. My interests are quite diverse - vision, robotics, data science, mathematics, physics, stock markets and I try my best to stay connected with the latest of updates in these areas. You can find my CV here. I am looking for internship opportunities starting May 2027 across AI research and applied development, with interest in both advancing core methods and translating them into high-impact real world solutions.

Vineet Bhat

Hi there!

Recent News