Unnat Jain
Biography
I am an Assistant Professor of Computer Science at the University of California, Irvine. Toward building general-purpose embodied intelligence, my research focuses on the intersection of computer vision (perception) and robot learning (action).
I have worked across industry, academia, and startups at Meta‘s Fundamental AI Research (FAIR) Labs, Carnegie Mellon University, and Skild AI, collaborating with Abhinav Gupta, Deepak Pathak, and Xinlei Chen. I received my PhD from UIUC, advised by Alex Schwing and Svetlana Lazebnik, and previously graduated from IIT Kanpur.
Opportunities
I am actively seeking motivated students interested in joining my research group. If you mention your interests in working with me in your application, I will review them carefully.
Deadline for Ph.D. Applications: December 15th
UC Irvine is a resourceful, friendly, and warm ecosystem and the campus is ideal for learning-tinkering-building AI systems.
For Current UCI Students: If you are interested in collaborating, please email me with:
- Your resume.
- Your UCI transcript.
- A description of your research interests, including your performance in relevant courses (AI/ML).
Core Research Themes
Accelerate generalization and scale-up embodied intelligence via:
- Vision-Language-Action Models: Efficient pre-, mid-, post-training strategies.
- Human-to-Robot Learning: Extracting action insights from human videos.
- Sim-to-Real Transfer: Scaling embodied AI using advanced simulation.
- Pre-training & Self-Supervised Learning: Adapting self-supervision lessons from CV/NLP to embodied agents.
- Multi-Agent Learning: Designing systems for collaborative tasks requiring multiple agents or robots.
Education
Ph.D., University of Illinois at Urbana-Champaign (UIUC)
B.Tech., Indian Institute of Technology (IIT Kanpur)
Research Areas
AI, ML and Natural Language Processing
Producing machines to automate tasks requiring intelligent behavior...
Computer Graphics and Vision
Generating, capturing, representing, rendering and interacting with synthetic and real-world images and video...