Teaching robots to see, reason, and act in the real world.

I am an Applied Scientist II at Amazon Robotics, working on humanoid manipulation and whole-body control, and collaborating with the Fauna Robotics group on Vision-Language-Action (VLA) pose-training.

My research spans 3D Vision & Robotics, Vision-Language-Action models, Generative AI, and Multimodal Learning (Vision + X), with applications reaching into Medical Image Analysis .

I recently completed my Ph.D. in Computer Science at Stony Brook University, advised by Prof. Zhaozheng Yin, after two summers at Amazon solving perception and manipulation problems in embodied AI. Earlier, I was a Data Scientist at Tata Digital and earned my B.E. from Jadavpur University.