Summary
Deepak Sridhar is a PhD student and Graduate Teaching Assistant at UC San Diego with nine years of experience advancing computer vision, particularly multimodal generative models and efficient perceptual systems. His recent research develops a diffusion-model framework that improves prompt compliance, controllability, and editable outputs across images, audio, video, and 3D—work showcased on a public project page. Prior to academia he led deployable, low-resource vision solutions at Huawei, shipping real-time hand-pose, gesture, and face models to Smart TVs and flagship phones and placing second in the ActivityNet temporal localization challenge. He bridges foundational vision problems (classification, detection, 2D/3D pose) with practical production constraints, and has hands-on experience adapting large foundational models for modular, reusable pipelines. Based in San Diego, he also contributes to teaching and community programs, reflecting a blend of research depth and product-oriented engineering.
9 years of coding experience
6 years of employment as a software developer
High School, High School at Sri Sarada Secondary School
Bachelor’s Degree, Instrumentation and Control, Bachelor’s Degree, Instrumentation and Control at National Institute of Technology, Tiruchirappalli
Master’s Degree, Electrical and Computer Engineering, Master’s Degree, Electrical and Computer Engineering at McGill University
Mathematics and Computer Science, Mathematics and Computer Science at St. John's Senior Secondary School
University of California, San Diego
English, Tamil, Hindi