publications

My publications, newest first. Selected papers are also shown on the home page.

2027

  1. Bring Back Language to Actions: Restoring VLM Capabilities in VLA Models via Parameter Merging
    Mohamed Salim Aissi, Olivier Sigaud, Laure Soulier, and 1 more author
    In Proceedings of the Conference of the European Chapter of the Association for Computational Linguistics (EACL), Main Conference, 2027
    Also accepted at the NeurIPS 2026 Workshop RoboPAD (Paris). arXiv coming soon

2026

  1. PRISM: Perception Reasoning Interleaved for Sequential Decision Making
    Mohamed Salim Aissi, Clemence Grislain, Clement Romac, and 4 more authors
    In International Conference on Machine Learning (ICML), 2026

2025

  1. Reinforcement Learning for Aligning Large Language Models Agents with Interactive Environments: Quantifying and Mitigating Prompt Overfitting
    Mohamed Salim Aissi, Clement Romac, Thomas Carta, and 5 more authors
    In Findings of the Association for Computational Linguistics: NAACL 2025, 2025
  2. Preprint
    viper.png
    VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making
    Mohamed Salim Aissi, Clemence Grislain, Mohamed Chetouani, and 3 more authors
    2025
  3. TALN
    naacl.png
    Apprentissage par renforcement pour l’alignement des agents LLMs avec des environnements interactifs : quantification et réduction du surapprentissage aux prompts
    Mohamed Salim Aissi, Clement Romac, Thomas Carta, and 5 more authors
    In Actes de TALN 2025, 2025