- Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment (NeurIPS 2025)
- Nile-Chat: Egyptian Language Models for Arabic and Latin Scripts (ArabicNLP 2025)
- Atlas-Chat: Adapting Large Language Models for Low-Resource Moroccan Arabic Dialect (LoResLM@COLING 2025, Best Paper Award)
- GreekBART: The First Pretrained Greek Sequence-to-Sequence Model (LREC-COLING 2024)
- Prot2Text: Multimodal Protein's Function Generation with GNNs and Transformers (AAAI 2024)
- Word sense induction with agglomerative clustering and mutual information maximization (AI Open Journal)
- Evaluation of Word Embeddings from Large-Scale French Web Content (CNIA 2022)
- Political Communities on Twitter: Case Study for the 2022 French Presidential Election (PoliticalNLP 2022)
Research Experience
Currently working at IFM Paris (MBZUAI Institute of Foundation Models). Previously, a Ph.D. candidate at LIX (École Polytechnique) with the DaSciM team.
Education
Ph.D. in Computer Science, Data, and AI from Institut Polytechnique de Paris, supervised by Prof. Michalis Vazirgiannis; Master's degree in Data Science from Institut Polytechnique de Paris; Engineering degree in Data Science from Telecom Paris; Engineering degree in Computer Science and Telecommunication from Lebanese University, Faculty of Engineering 1.
Background
Research Interests: Natural language processing, pretrained language models, and their applications. Field: Computer science, data, and AI. Brief Introduction: An engineer at IFM Paris (MBZUAI Institute of Foundation Models) focusing on NLP and pretrained language model applications.
Miscellany
Personal Interests: Passionate about the intersection of technology and linguistics.