@article{radev2026scheme,title={The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems},author={Radev, Nikolay and Haas, Lennart and Arnav, Benjamin and Bernabeu-Pérez, Pablo},year={2026},}
@article{koran2026ensemble,title={Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute},author={Koran, Eugene and Yun, Yejun and Tetef, Samantha and Arnav, Benjamin and Bernabeu-Pérez, Pablo},year={2026},}
@inproceedings{lin2026c3,title={Same Question, Different Lies: Cross-Context Consistency (C³) for Black-Box Sandbagging Detection},author={Lin, Yulong and Bernabeu-Pérez, Pablo and Arnav, Benjamin and Wells, Lennie and Phuong, Mary},booktitle={ICML 2026},year={2026},}
@inproceedings{seshadri2026clustering,title={Cross-Layer Clustering for Stochastic Parameter Decomposition},author={Seshadri, Saman and Digilov, Jack and Esla, Sean and Hu, Nathan Zixia and Ivanitskiy, Michael and Bernabeu-Pérez, Pablo},booktitle={ICLR 2026 Workshop on Latent \& Implicit Thinking -- Going Beyond CoT Reasoning},year={2026},}
@inproceedings{aldahik2025enhancing,title={Enhancing Monitoring in AI Control through Trusted Debate},author={Al Dahik, Ghassan and Xu, Ruize and Singh, Satvik and Kiunga, Leon and Bernabeu-Pérez, Pablo},booktitle={Socially Responsible and Trustworthy Foundation Models at NeurIPS 2025},year={2025},}
Preprint
Capability Pressure Amplifies Reward Hacking, Not Sophistication
@article{lin2025capabilitypressure,title={Capability Pressure Amplifies Reward Hacking, Not Sophistication},author={Lin, Kuan-Yen and Bernabeu-Pérez, Pablo and Feng, Shi},year={2025},}
@inproceedings{arnav2025cotredhandedstresstesting,title={CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring},author={Arnav, Benjamin and Bernabeu-Pérez, Pablo and Helm-Burger, Nathan and Kostolansky, Tim and Whittingham, Hannes and Phuong, Mary},booktitle={NeurIPS},year={2025},}
Dario Garcia-Gasulla, Jordi Bayarri-Planas, Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Adrian Tormos, Daniel Hinjos, Pablo Bernabeu-Pérez, Anna Arias-Duart, Pablo Agustin Martin-Torres, Marta Gonzalez-Mallo, Sergio Alvarez-Napagao, Eduard Ayguadé-Parra, and Ulises Cortés
@article{garciagasulla2025aloefamilyrecipeopen,title={The Aloe Family Recipe for Open and Specialized Healthcare LLMs},author={Garcia-Gasulla, Dario and Bayarri-Planas, Jordi and Gururajan, Ashwin Kumar and Lopez-Cuena, Enrique and Tormos, Adrian and Hinjos, Daniel and Bernabeu-Pérez, Pablo and Arias-Duart, Anna and Martin-Torres, Pablo Agustin and Gonzalez-Mallo, Marta and Alvarez-Napagao, Sergio and Ayguadé-Parra, Eduard and Cortés, Ulises},journal={npj Digital Medicine},year={2025},}
Anna Arias-Duart, Pablo Agustin Martin-Torres, Daniel Hinjos, Pablo Bernabeu-Pérez, Lucia Urcelay-Ganzabal, Marta Gonzalez-Mallo, Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Sergio Alvarez-Napagao, and Dario Garcia-Gasulla
@inproceedings{arias2025automatic,title={Automatic Evaluation of Healthcare LLMs Beyond Question Answering},author={Arias-Duart, Anna and Martin-Torres, Pablo Agustin and Hinjos, Daniel and Bernabeu-Pérez, Pablo and Urcelay-Ganzabal, Lucia and Gonzalez-Mallo, Marta and Gururajan, Ashwin Kumar and Lopez-Cuena, Enrique and Alvarez-Napagao, Sergio and Garcia-Gasulla, Dario},booktitle={NAACL},year={2025},}
@inproceedings{bernabeu2025synthetic,title={Present and Future Generalization of Synthetic Image Detectors},author={Bernabeu-Pérez, Pablo and Lopez-Cuena, Enrique and Garcia-Gasulla, Dario},booktitle={European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases},year={2025},}
Ashwin Kumar Gururajan, Enrique Lopez-Cuena, Jordi Bayarri-Planas, Adrian Tormos, Daniel Hinjos, Pablo Bernabeu-Pérez, Anna Arias-Duart, Pablo Agustin Martin-Torres, Lucia Urcelay-Ganzabal, Marta Gonzalez-Mallo, Sergio Alvarez-Napagao, Eduard Ayguadé-Parra, Ulises Cortés, and Dario Garcia-Gasulla
@article{gururajan2024aloefamilyfinetunedopen,title={Aloe: A Family of Fine-tuned Open Healthcare LLMs},author={Gururajan, Ashwin Kumar and Lopez-Cuena, Enrique and Bayarri-Planas, Jordi and Tormos, Adrian and Hinjos, Daniel and Bernabeu-Pérez, Pablo and Arias-Duart, Anna and Martin-Torres, Pablo Agustin and Urcelay-Ganzabal, Lucia and Gonzalez-Mallo, Marta and Alvarez-Napagao, Sergio and Ayguadé-Parra, Eduard and Cortés, Ulises and Garcia-Gasulla, Dario},year={2024},}