Robert McCarthy

PhD student, University College London, University of London

Joined

August 2023

Names

Robert McCarthy (Preferred)

Emails

****@ucdconnect.ie (Confirmed)

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

****@gmail.com (Confirmed)

Personal Links

Career & Education History

PhD student

University College London, University of London (ucl.ac.uk)

2022 – 2026

MS student

University College Dublin (ucd.ie)

2019 – 2021

Advisors, Relations & Conflicts

No relations added

Expertise

LLM Safety & Alignment

2024 – Present

Robot Learning

2020 – 2024

Publications

Early Signs of Steganographic Capabilities in Frontier LLMs
Artur Zolkowski, Kei Nishimura-Gasparian, Robert McCarthy, Roland S. Zimmermann, David Lindner
- ICLR 2026 Poster
- Readers: Everyone
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Joey Skaf, Luis Ibañez-Lissen, Robert McCarthy, Connor Watts, Vasil Georgiv, Hannes Whittingham, Lorena González-Manzano, David Lindner, Cameron Tice, Edward James Young, Puria Radmard
- CoRR 2025
- Readers: Everyone
Large language models can learn and generalize steganographic chain-of-thought under process supervision
Robert McCarthy, Joey SKAF, Luis Ibanez-Lissen, Vasil Georgiev, Connor Watts, Hannes Whittingham, Lorena Gonzalez-Manzano, Cameron Tice, Edward James Young, Puria Radmard, David Lindner
- NeurIPS 2025 poster
- Readers: Everyone
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Yohan Mathew, Robert McCarthy, Joan Velja, Ollie Matthews, Christian Schroeder de Witt, Dylan Cope, Nandi Schoots
- Submitted to ICLR 2025
- Readers: Everyone
Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs
Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schroeder de Witt, Dylan Cope, Nandi Schoots
- SafeGenAi Poster
- Readers: Everyone
Emergence of Steganography Between Large Language Models
Yohan Mathew, Robert McCarthy, Joan Velja, Ollie Matthews, Nandi Schoots, Dylan Cope
- SoLaR Poster
- Readers: Everyone
Steganography in Large Language Models: Investigating Emergence and Mitigations
Yohan Mathew, Robert McCarthy, Ollie Matthews, Joan Velja, Nandi Schoots, Dylan Cope
- Red Teaming GenAI Workshop @ NeurIPS'24 Poster
- Readers: Everyone
Identifying Expert Behavior in Offline Training Datasets Improves Behavioral Cloning of Robotic Manipulation Policies
Qiang Wang, Robert McCarthy, David Cordova Bulens, Francisco Roldan Sanchez, Kevin McGuinness, Noel E. O'Connor, Stephen J. Redmond
- IEEE Robotics Autom. Lett. 2024
- Readers: Everyone
Safe Value Functions: Learned Critics as Hard Safety Constraints
Daniel Chee Hian Tan, Robert McCarthy, Fernando Acero, Andromachi Maria Delfaki, Zhibin Li, Dimitrios Kanoulas
- CASE 2024
- Readers: Everyone
Towards Generalist Robot Learning from Internet Video: A Survey
Robert McCarthy, Daniel Chee Hian Tan, Dominik Schmidt, Fernando Acero, Nathan Herr, Yilun Du, Thomas George Thuruthel, Zhibin Li
- CoRR 2024
- Readers: Everyone

View all 24 publications

Co-Authors

View all 94 co-authors