Christos Thrampoulidis

Assistant Professor, University of British Columbia

Joined

July 2019

Names

Emails

****@ucsb.edu (Confirmed)

****@ece.ubc.ca (Confirmed)

Personal Links

Homepage

DBLP

Career & Education History

Assistant Professor

University of British Columbia (ubc.ca)

2021 – Present

Assistant Professor

UC Santa Barbara (ucsb.edu)

2018 – 2020

Advisors, Relations & Conflicts

Postdoc Advisor

Greg Wornell

2016 – 2018

PhD Advisor

Babak Hassibi

2011 – 2016

Expertise

deep-learning

Present

machine learning theory

Present

optimization theory

Present

high-dimensional statistics

Present

Publications

Beyond Co-occurence: A Study of Early-stage Semantic Geometry in Next-Token Prediction
Yize Zhao, Isabel Papadimitriou, Christos Thrampoulidis
- ICLR 2026 Workshop GRaM Poster
- Readers: Everyone
In-Context Benign Overfitting: A Feature-Selection Model in In-Context Linear Regression
Puneesh Deora, Bhavya Vasudeva, Christos Thrampoulidis
- Sci4DL 2026
- Readers: Everyone
Understanding Contextual Recall in Transformers: How Finetuning Enables In-Context Reasoning over Pretraining Knowledge
Bhavya Vasudeva, Puneesh Deora, Alberto Bietti, Vatsal Sharan, Christos Thrampoulidis
- Sci4DL 2026
- Readers: Everyone
On Group Relative Policy Optimization Collapse in Agent Search: The Lazy Likelihood-Displacement
Wenlong Deng, Yushu Li, Boying Gong, Yi Ren, Christos Thrampoulidis, Xiaoxiao Li
- LLA 2026 Poster
- Readers: Everyone
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients
Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
- Accepted by TMLR
- Readers: Everyone
Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection
Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du, Ivan Moshkov, George Armstrong, Renjie Liao, Christos Thrampoulidis, Igor Gitman
- MATH-AI 2025 Poster
- Readers: Everyone
Short-Context dominance: How Much Local Context Natural Language Actually Needs?
Vala Vakilian, Zimeng Wang, Ankit Singh Rawat, Christos Thrampoulidis
- ICLR 2026 Conference Desk Rejected Submission
- Readers: Everyone
How Muon’s Spectral Design Benefits Generalization: A Study on Imbalanced Data
Bhavya Vasudeva, Puneesh Deora, Yize Zhao, Vatsal Sharan, Christos Thrampoulidis
- ICLR 2026 Poster
- Readers: Everyone
Token Hidden Reward: Steering Exploration-Exploitation in Group Relative Deep Reinforcement Learning
Wenlong Deng, Yi Ren, Yushu Li, Boying Gong, Danica J. Sutherland, Xiaoxiao Li, Christos Thrampoulidis
- ICLR 2026 Poster
- Readers: Everyone
Efficient Forward-Only Data Valuation For LLMs and VLMs
Wenlong Deng, Qi Zeng, Jiaming Zhang, Minghui Chen, Zixin Ding, Christos Thrampoulidis, Boying Gong, Xiaoxiao Li
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone

View all 71 publications

Co-Authors

View all 71 co-authors