Documents publiés en "2025"

Communication écrite

Thakkar, M., Fournier, Q., Riemer, M., Chen, P.-Y., Zouaq, A., Das, P., & Anbil Parthipan, S. C. (juillet 2025). Combining Domain and Alignment Vectors Provides Better Knowledge-Safety Trade-offs in LLMs [Communication écrite]. 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), Vienna, Austria. Lien externe

Vattikonda, D., Ravichandran, S., Penaloza, E., Nekoei, H., Le Sellier de Chezelles, T., Thakkar, M., Angelard-Gontier, N., Muñoz-Mármol, M., Omidi Shayegan, S., Raimondo, S., Liu, X., Drouin, A., Piché, A., & Caccia, M. (décembre 2025). How to Train Your LLM Web Agent: A Statistical Diagnosis [Communication écrite]. 39th Conference on Neural Information Processing Systems (NeurIPS 2025), San Diego, CA, USA. Lien externe