CV
Curriculum vitae
Research scientist in Document Intelligence. The PDF has the same content in print layout.
Professional Summary
Enseignant-Chercheur Contractuel and Research Scientist working at the intersection of Multimodal AI, NLP, and Computer Vision. I design and lead applied research translating state-of-the-art methods into robust, scalable systems for document understanding and multimodal learning. My work includes vision-language architectures and efficient training/inference strategies, with 22 peer-reviewed publications (285 citations, h-index 9, Google Scholar, September 2026) in venues such as Pattern Recognition, WACV, and ICDAR. I have secured 501,500 EUR in competitive funding, coordinated international collaborations, and managed large-scale computing to deliver production-grade outcomes.
Research Profile
Enseignant-Chercheur Contractuel in Computer Science specializing in multimodal document analysis, information extraction, and cross-modal learning. Research spans document classification, few-shot learning, retrieval, abstractive summarization, and document QA, with additional focus on low-resource scene-text recognition, fairness and ethics of LLMs/LMMs, data privacy, and explainability.
Research Metrics and Impact
- Publications: 29 in total, 22 peer-reviewed; 285 citations; h-index 9 (Google Scholar, September 2026)
- Funding secured: 501,500 EUR as PI/Co-PI
- PhD supervision: ongoing co-supervision of doctoral students
- Peer review: PR, IJCV, EAAI; PC/reviewer for ICDAR, ICPR, ICIP
Academic Appointments
- Sep 2025 - Present: Enseignant-Chercheur Contractuel, IRISA-Lab, ESIR, Université de Rennes, France (SHADOC Team)
- Research: Multimodal AI, document analysis and understanding, NLP, computer vision
- Teaching: undergraduate and graduate computer science courses
- Sep 2023 - Aug 2025: Associate Professor (Maître de Conférences), L3i-Lab, La Rochelle Université, France
- Head of course element: Advanced Database Management Systems
- Organizer/moderator: Research Reading Group; seminars on deep multimodal learning
- Jan 2023 - Aug 2023: Postdoctoral Researcher and Lecturer, L3i-Lab, La Rochelle Université, France
- Research: Multimodal document analysis, classification, retrieval, few-shot learning
Research Experience
- Dec 2019 - Dec 2022: PhD Researcher and Lecturer, L3i-Lab, La Rochelle Université, France
- Developed efficient multimodal AI frameworks for document analysis and understanding
- Publications during PhD in Pattern Recognition, IJDAR, ICDAR, ICIP
- Feb 2019 - Jul 2019: Research Intern, L3i-Lab, La Rochelle Université
- Face authentication with deep learning for biometric anti-fraud
Professional Experience
- Jun 2018 - Aug 2018: Data Science Engineer (Intern), Inlog Solutions, Rabat, Morocco
- Fingerprint verification; data mining and client segmentation
- Jun 2017 - Aug 2017: Software Developer (Intern), Lotus IT, Tangier, Morocco
- Web development project
Education
- Ph.D. in Computer Science and Applications, La Rochelle Université, France (2019-2022)
- Thesis: Multimodal Document Understanding with Unified Vision and Language Cross-Modal Learning
- European Doctorate Label (CVC, Universitat Autonoma de Barcelona)
- Engineering Degree (M.Eng) in Telecommunications Engineering and IT, INPT, Morocco (2016-2019)
- Preparatory Classes for Engineering Schools (CPGE), Al-Qalam, Morocco (2013-2016)
Teaching Experience
- Total teaching hours: 800+ HeTD; 200+ students taught (2020-2025)
- Course coordination: Advanced Database Management Systems; Foundations of AI
- Master level: Neural Networks; Big Data Systems; Secure Networks and Storage; Web Technologies; Research and Scientific Project
- Bachelor level: Advanced Database Management Systems; Advanced Database Modeling; Intro to Computer Systems
Student Supervision and Mentoring
- PhD co-supervision (current): topics include low-resource scene-text recognition, explainable multimodal understanding, and federated learning
- Thesis supervision: multiple M1/M2 and B3 projects across France, India, and Vietnam, with workshop publications
Research Grants and Funding (501.5K EUR)
- PI: DocInnovate (ACI JCJC 2024), 7,000 EUR
- Co-PI: FELM (EU-CONEXUS 2025-2027), 153,000 EUR
- Co-PI: FlexChain (2025-2027), 124,000 EUR
- Co-PI: ModamPadoc (RNA-LRU 2025-2027), 120,000 EUR
- Co-PI: AI for ECO-WELLNESS (PHC PERIDOT 2024-2026), 28,000 EUR
- Additional projects: 69,500 EUR
Publications
The complete, searchable list is on the publications page. By type:
Journals (4)
- 2026: HSB-GDL: A Heterogeneous Subgraph Benchmark for Classification and Query Spotting (IJDAR 2026)
- 2025: Confidence-Based Knowledge Distillation to Reduce Training Costs and Carbon Footprint for Low-Resource Neural Machine Translation (Applied Sciences 2025)
- 2023: VLCDoC: Vision-Language Contrastive Pre-Training Model for Cross-Modal Document Classification (Pattern Recognition 2023)
- 2021: EAML: Ensemble Self-Attention-Based Mutual Learning Network for Document Image Classification (IJDAR 2021)
Conferences (9)
- 2026: Terminology-Aware Retrieval-Augmented Knowledge Distillation for Biomedical Neural Machine Translation (EAMT 2026)
- 2026: Investigating Model Compression for Neural Machine Translation in the Biomedical Domain (AICS 2025)
- 2025: WildKhmerST: A Comprehensive Dataset and Benchmark for Khmer Scene Text Detection and Recognition in the Wild (ICDAR 2025)
- 2025: GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification (WACV 2025)
- 2024: KhmerST: A Low-Resource Khmer Scene Text Detection and Recognition Benchmark (ACCV 2024)
- 2024: Multimodal Adaptive Inference for Document Image Classification with Anytime Early Exiting (ICDAR 2024)
- 2024: LLMChain: Blockchain-Based Reputation System for Sharing and Evaluating Large Language Models (COMPSAC 2024)
- 2024: State-of-the-Art Khmer Text Recognition Using Deep Learning Models (ACET 2024)
- 2020: Cross-Modal Deep Networks for Document Image Classification (ICIP 2020)
Workshops (9)
- 2026: BHCP-DOC: A Real-World Bilingual Dataset for Handwritten Clinical Prescription Detection and Recognition (ICPR Workshops 2026)
- 2026: Cross-Lingual Transfer for Complex Scripts: A Benchmark on End-to-End Khmer Scene Text Spotting (WACV Workshops 2026)
- 2025: Cross-Lingual Learning for Low-Resource Khmer Scene Text Detection and Recognition (ICDAR Workshops 2025)
- 2025: Visual Text Generation in Khmer Language: Challenges and Trends with Diffusion Models (ICDAR Workshops 2025)
- 2025: Fusion of GNN and GBDT Models for Graph and Node Classification (GbRPR 2025)
- 2025: IDTrust: Deep Identity Document Quality Detection with Bandpass Filtering (WACV Workshops 2025)
- 2025: DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization (WACV Workshops 2025)
- 2020: Visual and Textual Deep Feature Fusion for Document Image Classification (CVPR Workshops 2020)
- 2019: Face Detection in Camera Captured Images of Identity Documents Under Challenging Conditions (ICDAR Workshops 2019)
Preprints (6)
- 2026: An Empirical Study of Recent Large Language Models for Knowledge Graph to Text Generation on Standard Benchmarks (arXiv 2026)
- 2026: Fresh at Decision, Stale at Action: Routing New Information to LLM Decisions Already Made (arXiv 2026)
- 2026: Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligence (arXiv 2026)
- 2025: MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora (arXiv 2025)
- 2025: Evaluating the Impact of Khmer Font Types on Text Recognition (arXiv 2025)
- 2023: TransferDoc: A Self-Supervised Transferable Document Representation Learning Model Unifying Vision and Language (SSRN 2023)
Thesis (1)
- 2022: Multimodal Document Understanding with Unified Vision and Language Cross-Modal Learning (PhD thesis 2022)
Research Collaborations
- International: CVC (UAB, Spain), KU Leuven (Belgium), L2TI (France), SETU (Ireland), Josef Stefan Institute (Slovenia), USTH (Vietnam), Cambodia Academy of Digital Technology, MNS University (Pakistan)
- Industry: Allread ML Technologies (Spain), Siren Company (France)
Academic Service and Leadership
- Organizer and moderator: Research Reading Group (L3i, 2023-present)
- Organizer: Seminars on deep multimodal learning (L3i)
- Organizing committee: ICPR 2024 Call for Competitions; DAS 2022
- Peer review: PR, IJCV, EAAI, Neurocomputing; ICDAR, ICPR, ICIP, LREC-COLING
Invited Talks and Presentations
- LORIA-Lab, Nancy: Pareto-efficient multimodal document understanding
- L3i, La Rochelle: Semantic multimodal document representation learning (2022)
- CVC, Barcelona: Multimodal document understanding
Technical Skills
- Multimodal AI: CLIP, BLIP, LayoutLM, LLaVA; multimodal fusion; document understanding
- Computer Vision: OCR, scene-text detection/recognition, CNNs, ViTs, GANs
- NLP: GPT, BERT, T5, RoBERTa; NER, information extraction, semantic search
- MLOps/HPC: MLflow, TensorBoard, Docker, SLURM; GPU cluster administration
- Programming: Python, SQL, JavaScript, C++
- Tools: Git, Jupyter, PostgreSQL, MongoDB, Elasticsearch, FAISS, AWS, Google Cloud
Languages
- French (fluent)
- English (fluent)
- Arabic (native)