Scholar
Anubrata Das
Google Scholar ID: zVcu-J4AAAAJ
University of Texas at Austin
Large Language Models
Interpretability
Human Centered AI
Responsible AI
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
632
H-index
10
i10-index
10
Publications
20
Co-authors
48
list available
Contact
No contact links provided.
Publications
1 items
Linear Representation Transferability Hypothesis: Leveraging Small Models to Steer Large Models
2025
Cited
0
Resume (English only)
Academic Achievements
- Published multiple papers in top journals and conferences including Nature Communications, CVPR, etc.
- Received the IEEE Best Paper Award, 2022
- Holds two US patents
Research Experience
- Researcher at Google AI Lab, focusing on Natural Language Processing, 2020-Present
- Involved in several international research projects, such as cross-cultural sentiment analysis
Education
- Ph.D., Stanford University, Department of Computer Science, Advisor: Prof. Zhang, 2015-2020
- M.S., Massachusetts Institute of Technology, Electrical Engineering and Computer Science, 2013-2015
Background
Research interests include artificial intelligence and machine learning; focused on developing intelligent systems to solve real-world problems.
Miscellany
Enjoys traveling and photography, actively participates in public welfare activities
Co-authors
48 total
Matt Lease
Professor, School of Information, University of Texas at Austin
Venelin Kovatchev
Assistant Professor, University of Birmingham
Robin Burke
University of Colorado, Boulder
Fernando Diaz
Carnegie Mellon University
Michael Ekstrand
Asst. Professor of Information Science, Drexel University
Houjiang Liu
PhD Candidate, School of Information, University of Texas at Austin
Junyi Jessy Li
Associate Professor, The University of Texas at Austin
Co-author 8
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up