Sumanth Gurram

By trade, I am an AI engineer based in San Francisco, CA. I studied Electrical Engineering Computer Science (EECS) and Business at UC Berkeley through the M.E.T. Program.

Email  /  CV  /  LinkedIn  /  Github

profile photo
Engineering

I'm currently building AI agents at Decagon. Previously, I was a product engineer at Zip. Some of my past internship experience includes infra for self-driving cars at Nuro, and training robots in simulation at Apple.

Research

My research interests are machine learning and distributed computing. I've worked on multi-modal video understanding at BAIR, interactive image segmentation at Facebook AI Research and SkyPilot under Ion Stoica.

fast-texture Segment Anything
Alexander Kirillov Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick ICCV, 2023, Oral (was recognized as project contributor)

We introduce the Segment Anything project: a new task, model, and dataset for image segmentation.

fast-texture LAVA: Language Audio Vision Alignment for Contrastive Video Pre-Training
Sumanth Gurram, Andy Fang, David Chan, John Canny
ICML Workshop, 2022

We use audio, visual and text data from videos to learn representations in a contrastive manner for downstream action recognition.


Thanks for template