• PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models

  Dhouib Mohamed, Davide Buscaldi, Vanier Sonia, Aymen Shabou

  published at CVPR '25

• Predicting memorization within Large Language Models fine-tuned for classification

  Jérémie Dentan, Davide Buscaldi, Aymen Shabou, Sonia Vanier

• Guess or Recall? Training CNNs to Classify and Localize Memorization in LLMs

  Jérémie Dentan, Davide Buscaldi, Sonia Vanier

• Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoders

  Mathis Le Bail, Jérémie Dentan, Davide Buscaldi, Sonia Vanier

• Coherent Multi-Table Data Synthesis for Tabular and Time-Series Data with GANs

  Clement Elliker, Emeric Tonnelier, Aymen Shabou

  published at CODASPY '24

• Reconstructing training data from document understanding models

  Jérémie Dentan, Arnaud Paran, Aymen Shabou

  pre-print at 33rd USENIX Security Symposium

• DocParser: End-to-end OCR-free Information Extraction from Visually Rich Documents

  Mohamed Dhouib, Ghassen Bettaieb, Aymen Shabou

  Accepted at ICDAR, 2023

• Evaluating Adversarial Robustness on Document Image Classification

  Timothée Fronteau, Arnaud Paran, Aymen Shabou

  Accepted at ICDAR, 2023

• VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach

  Mohamed Kerroumi, Othmane Sayem, Aymen Shabou

  Accepted at ICDAR, 2021

• EfficientQA : a RoBERTa Based Phrase-Indexed Question-Answering System

  Sofian Chaybouti, Achraf Saghe, Aymen Shabou

• MIX : a Multi-task Learning Approach to Solve Open-Domain Question Answering

  Sofian Chaybouti, Achraf Saghe, Aymen Shabou

• An email virtual assistant solution for customer services

  Aymen Shabou