Blog
Talks
CV
šĀ Google Scholar

Email: tharis at bu.edu
Hi! Iām Themis!
I am a third-year PhD student at Boston University, jointly advised by ***Krzysztof Onak*** and Venkatesh Saligrama. I did my undergrad at Dartmouth College advised by **Amit Chakrabarti.**
My research focuses on developing efficient and robust algorithms for Foundation Models. I am also interested in problems from different areas of theoretical computer science, including sublinear algorithms, learning theory and complexity.
Work Experience
- Research Intern, Google Research, AIRX Team (2026)
- Student Researcher, Google Research, hosted by **Maryam Karimzadehgan** (2025-2026)
- Research Intern, National Institute of Informatics, Tokyo, hosted by **Yuichi Yoshida** (2025)
- Software engineer, Windows Base Kernel Team, Microsoft (2021-2023)
- Software engineering intern, Windows Base Kernel Team, Microsoft (2020)
Publications
Foundation Models
Work on (mostly) Transformer models, efficient inference and intepretability.
- Layerwise Dynamics for In-Context Classification in Transformers: Lutz, Haris, Chandra, Gangrade, Saligrama ā ICML 2026 (Spotlight)
- Noise Stability of Transformer Models: Haris, Zhang, Yoshida ā ICLR 2026
- Compression Barriers for Autoregressive Transformers: Haris, Onak ā COLT 2025
- $k$NN Attention Demystified: A Theoretical Exploration for Scalable Transformers: Haris ā ICLR 2025
Theoretical Computer Science
Work mainly focused on sublinear algorithms for various TCS problems.
Submodular Functions