Yarin Gal

Associate Professor, University of Oxford

Joined

September 2016

Names

Yarin Gal (Preferred)

Yarin G

Emails

****@cs.ox.ac.uk (Confirmed)

****@cam.ac.uk (Confirmed)

****@gmail.com (Confirmed)

****@diffractive.ai (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Associate Professor

University of Oxford (ox.ac.uk)

2017 – Present

Advisors, Relations & Conflicts

PhD Advisor

Zoubin Ghahramani

2012 – 2016

Expertise

Bayesian deep learning

Present

Publications

Training Transformers for KV Cache Compressibility
Yoav Gelberg, Yam Eitan, Michael M. Bronstein, Yarin Gal, Haggai Maron
- HiLD at ICML 2026 Poster
- Readers: Everyone
Selective Safety Steering via Value-Filtered Decoding
Bat-Sheva Einbinder, Hen Davidov, Yee Whye Teh, Yarin Gal, Yaniv Romano
- AI4GOOD Workshop 2026 Regular
- Readers: Everyone
Boundary Point Jailbreaking of Black-Box LLMs
Xander Davies, Giorgi Giglemiani, Edmund Lau, Eric Winsor, Geoffrey Irving, Yarin Gal
- ICML 2026 AIWILD
- Readers: Everyone
Building Reliable Long-Form Generation via Hallucination Rejection Sampling
Lin Li, Georgia Channing, Suhaas M Bhat, Gabriel Davis Jones, Yarin Gal
- Agentic AI in the Wild: From Hallucinations to Reliable Autonomy Poster
- Readers: Everyone
Vision-Language Models Fail to Generalize Across Modalities
Yonatan Gideoni, Yoav Gelberg, Tim G. J. Rudner, Yarin Gal
- ICLR 2026 Re-Align Workshop
- Readers: Everyone
Deception in Dialogue: Evaluating and Mitigating Deceptive Behavior in Large Language Models
Marwa Abdulhai, Ryan Cheng, Aryansh Shrivastava, Natasha Jaques, Yarin Gal, Sergey Levine
- ICLR 2026 Trustworthy AI
- Readers: Everyone
Simple Baselines are Competitive with Code Evolution
Yonatan Gideoni, Sebastian Risi, Yarin Gal
- ICLR 2026 Workshop RSI Poster
- Readers: Everyone
Open Technical Problems in Open-Weight AI Model Risk Management
Stephen Casper, Kyle O'Brien, Shayne Longpre, Elizabeth Seger, Kevin Klyman, Rishi Bommasani, Aniruddha Nrusimha, Ilia Shumailov, Sören Mindermann, Steven Basart, Frank Rudzicz, Kellin Pelrine, Avijit Ghosh, Andrew Strait, Robert Kirk, Dan Hendrycks, Peter Henderson, J Zico Kolter, Geoffrey Irving, Yarin Gal et al. (2 additional authors not shown)
- Accepted by TMLR
- Readers: Everyone
Deception in Dialogue: Evaluating and Mitigating Deceptive Behavior in Large Language Models
Marwa Abdulhai, Ryan Cheng, Aryansh Shrivastava, Natasha Jaques, Yarin Gal, Sergey Levine
- Submitted to ICLR 2026
- Readers: Everyone
Predicting Weak-to-Strong Generalization from Latent Representations
Ben Wilop, Christian Schroeder de Witt, Yarin Gal, Philip Torr, Constantin Venhoff
- Submitted to ICLR 2026
- Readers: Everyone

View all 211 publications

Co-Authors

View all 480 co-authors