Joan Velja

According to our database, Joan Velja authored at least 5 papers between 2024 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

When can we trust untrusted monitoring? A safety case sketch across collusion strategies.

Nelson Gardner-Challis, Jonathan Bostock, Georgiy Kozhevnikov, Morgan Sinclaire, Joan Velja, Alessandro Abate, Charlie Griffin

CoRR, February, 2026

2025

Modular Training of Neural Networks aids Interpretability.

Satvik Golechha, Maheep Chaudhary, Joan Velja, Alessandro Abate, Nandi Schoots

CoRR, February, 2025

Hidden in Plain Text: Emergence & Mitigation of Steganographic Collusion in LLMs.

Yohan Mathew, Ollie Matthews, Robert McCarthy, Joan Velja, Christian Schröder de Witt, Dylan Cope, Nandi Schoots

Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics, 2025

2024

'Explaining RL Decisions with Trajectories': A Reproducibility Study.

Karim Abdel Sadek, Matteo Nulli, Joan Velja, Jort Vincenti

Trans. Mach. Learn. Res., 2024

Dynamic Vocabulary Pruning in Early-Exit LLMs.

Jort Vincenti, Karim Abdel Sadek, Joan Velja, Matteo Nulli, Metod Jazbec

CoRR, 2024