Research
My main interests are mech interp, generalization, reward hacking, agent coordination, and science of evaluations.
2026
- Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors
Juan-Pablo Rivera, Ari Spiesberger, Juan J. Vazquez, Arun Jose, Axel Ahlqvist, Adeline Kassler, Meru Gopalan, Sandy Tanwisuth, John Hughes
- BAITBENCH: Measuring Agent Reward Hacking with Optional Shortcuts Planted in ML Tasks
Pradyumna Shyama Prasad*, Meiri Anto*, Leon Eshuijs*, Julian Moncarz, Kaustubh Kislay, Juan J. Vazquez*
- Soft Contamination Means Benchmarks Test Shallow Generalization
Ari Spiesberger*, Juan J. Vazquez*, Nicky Pochinkov, Tomáš Gavenčiak, Peli Grietzer, Gavin Leech, Nandi Schoots
2025
- Evaluating LLM Agent Collusion in Double Auctions
Kushal Agrawal*, Verona Teo*, Juan J. Vazquez*, Sudarsh Kunnavakkam, Vishak Srikanth, Andy Liu
2024
- Questionable practices in machine learning
Gavin Leech*, Juan J. Vazquez*, Niclas Kupper, Misha Yagudin, Laurence Aitchison
- LuminLab: An AI-Powered Building Retrofit and Energy Modelling Platform
Kevin Credit, Qian Xiao, Jack Lehane, Juan J. Vazquez, Dan Liu, Leo De Figueiredo
2023
- Steering Language Models With Activation Engineering
Alexander Matt Turner, Lisa Thiergart, Gavin Leech, David Udell, Juan J. Vazquez, Ulisse Mini, Monte MacDiarmid
* equal contribution