Chaybouti, Sofian

3 publications

ICLR 2026 MaskInversion: Localized Embeddings via Optimization of Explainability Maps Walid Bousselham, Sofian Chaybouti, Christian Rupprecht, Vittorio Ferrari, Hilde Kuehne

ICCV 2025 LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity Walid Bousselham, Angie Boggust, Sofian Chaybouti, Hendrik Strobelt, Hilde Kuehne

NeurIPSW 2022 Meta-Learning of Black-Box Solvers Using Deep Reinforcement Learning Sofian Chaybouti, Ludovic Dos Santos, Cedric Malherbe, Aladin Virmaux