Walid Bousselham

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

DEX-AR: A Dynamic Explainability Method for Autoregressive Vision-Language Models

REVEAL: Advancing Relation-based Video Understanding for Video-Question-Answering

VOLD: Reasoning Transfer from LLMs to Vision-Language Models via On-Policy Distillation

MaskInversion: Localized Embeddings via Optimization of Explainability Maps

LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivity