Home » Teams » MLIA » Salim Aissi

  • Salim Aissi

  • PhD Student
  • Team: MLIA
  • Office: H01
  • Email: mohamed-salim.aissi@sorbonne-universite.fr

Publications

  • Mohamed Salim Aissi, Clément Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, et al.. Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting. NAACL 2025 - Findings of the Association for Computational Linguistics, Apr 2025, Albuquerque, United States. pp.7030-7046, ⟨10.18653/v1/2025.findings-naacl.390⟩. ⟨hal-05321901⟩
    [ HTTP | PDF ]
  • Mohamed Salim Aissi, Clément Romac, Thomas Carta, Sylvain Lamprier, Pierre-Yves Oudeyer, et al.. Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting. 2024. ⟨hal-04844077⟩
    [ HTTP ]
  • Diane Schuh, Mohamed-Salim Aissi, David Fierro, Hugo Scurto, Roberto Dell’orco, et al.. Mycelium Garden : Listening to and composing with the infra-world. « Soundstainability, making future from listening », XI FKL International Symposium on aspects of the soundscape, FKL-Forum Klanglandschaft; SUPSI - Scuola Universitaria Professionale della Svizzera Italiana; RSI Radio Televisione Svizzera di Lingua Italiana; UNIL Università di Losanna, Oct 2023, Lugano, Switzerland. ⟨hal-04847669⟩
    [ HTTP ]