Yogesh Balaji
I am a staff research scientist and research manager at NVIDIA Cosmos Lab. I graduated with a PhD in Computer Science from the University of Maryland, College Park, where I was advised by Prof. Rama Chellappa and Prof. Soheil Feizi. Prior to UMD, I obtained a B.Tech with a major in Electrical Engineering and a minor in Operations Research from the Indian Institute of Technology, Madras.
My research interests are in computer vision and machine learning, with a focus on large-scale generative modeling. I currently work on building world foundation models, where I focus on large-scale pretraining.
News
- 2026 NVIDIA Cosmos 3 launched at GTC Taipei — omnimodal world models for Physical AI.
- 2026 Serving as Area Chair for NeurIPS 2026.
- 2026 InfoTok accepted as an Oral at ICLR 2026.
Highlights
Publications
No publications in this category.
Experience
-
NVIDIA Research
Staff Research Scientist & Research Manager · 2021 – present
-
DeepMind
Research Intern, Summer 2020 · Large-scale continual learning
-
Facebook AI Research
Research Intern, Summer 2019 · Adversarial robustness
-
NEC Laboratories America
Research Intern, Summer 2018 · Text-conditioned video GANs
Awards
-
Ann G. Wylie Dissertation Fellowship
University of Maryland · 2020
-
Dean's Fellowship
University of Maryland · 2016 – 2018
Mentorship
I have had the privilege of working with and mentoring talented students and researchers.