Yao Xiao

CS Ph.D. candidate @ UIUC

Google Scholar
GitHub
X
Linkedin

About Me

I am a a final-year Ph.D. candidate in Computer Science at University of Illinois Urbana-Champaign, advised by Prof. Derek Hoiem.

My current research interests mainly lie in computer vision, especially in:

  • Closed-loop Planning: Complex tasks demand sequential decision-making under partial observability, where no single observation reveals the full state, and every decision must build on the history of what came before.

  • Memory Representation: How should an agent encode its past into a compact, rewritable state, one that helps the present without drowning it, and is re-encoded if needed?

  • Experience Retrieval: How do we recall exactly the right piece of the past at the right moment?

I'm always happy to collaborate on interesting projects, especially with self-motivated grad or undergrad students. If you're into my works or just want to chat, feel free to drop me an email!

Selected Works

For the full publication list, please refer to Google Scholar.

πŸ… TMLR 2025

TextRegion: Text-Aligned Region Tokens from Frozen Image-Text Models

Yao Xiao, Qiqian Fu, Heyi Tao, Yuqun Wu, Zhen Zhu, Derek Hoiem

Transactions on Machine Learning Research (TMLR), November 2025.
J2C Certification πŸ… (top ~10% among accepted TMLR papers)

[Paper] [Code] [Bibtex]

Blog

A space to share my thoughts and track my growth. I’ll keep it casual -- I’m a CS student, but this isn’t a technical blog.

β†’ Full list

Teaching

Services

Co-organizer: UIUC Computer Vision External Speaker Series β€” Interested speakers are welcome to reach out to register for upcoming sessions.

Reviewer: CVPR, ICCV, ECCV, ICLR, NeurIPS, WACV, IEEE Access.

Last Updated: 7/5/2026, 11:40:51 AM