CV

Publications

(QUIET DRONES) Deeplomatics: A deep-learning based multimodal approach for aerial drone detection and localization

Éric Bavu, Hadrien Pujol, Alexandre Garcia, Christophe Langrenne, Sébastien Hengy, et al.. Deeplomatics: A deep-learning based multimodal approach for aerial drone detection and localization. QUIET DRONES Second International e-Symposium on UAV/UAS Noise, INCE/Europe; CidB, Jun 2022, Paris, France. ⟨hal-03707115⟩

(TMLR) ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation

Karmim, Y., Ramzi, E., Fournier-S’niehotta, R., & Thome, N. (2024). ITEM: Improving Training and Evaluation of Message-Passing based GNNs for top-k recommendation. Transaction in Machine Learning Research (TMLR). https://arxiv.org/abs/2407.07912v1

(ECML2024 MLG Worshop) Temporal receptive field in dynamic graph learning: A comprehensive analysis

Karmim, Y., Yang, L., S’Niehotta, R. F., Chatelain, C., Adam, S., & Thome, N. (2024). Temporal receptive field in dynamic graph learning: A comprehensive analysis. ECML-PKDD Machine Learning on Graphs Workshop. https://hal.science/hal-04647025

(NeurIPS2024) Supra-Laplacian Encoding for Transformer on Dynamic Graphs

Karmim, Y., Lafon, M., Fournier S’niehotta Cedric, R., & Thome, N. (2024). Supra-Laplacian Encoding for Transformer on Dynamic Graphs. NeurIPS2024. https://arxiv.org/abs/2409.17986v1

Education

• B.S in Computer Science with honors, Sorbonne Université (former Pierre et Marie Curie), 2018
• 6 Month exchange Program during my B.S, Université de Montréal, Winter 2018
• M.S Data Learning and Knowledge (DAC), Sorbonne Université, 2020
• Ph.D in Dynamic Graph for GNN, Conservatoire National des Arts et Métiers (CNAM), 2024 (expected)

Work experience

• Summer 2024: Deep Learning consulting
  • RAKAM, Paris
  • Deployment of an LLM capable of reasoning on structured data for automatic tutorial generation.
• Oct 2021 - Oct 2024: PhD
  • VERTIGO, CNAM (Paris)
  • Designing Graph Neural Networks on Dynamic Graph. Application on Recommendation (ranking, collaborative filtering…)
  • Supervisor: Nicolas Thome and Raphaël Fournier S’niehotta
• Oct 2020 - Sep 2021: Research Engineer
  • VERTIGO, CNAM (Paris)
  • Deeplomatics project focus on drone detection. Also research on semi and self supervised methods for semantic segmentation.
  • Supervisor: Nicolas Thome
• Feb 2020 - Sep 2020: Research Intern
  • VERTIGO, CNAM (Paris)
  • Final year of Master Research internship on Computer Vision and Semantic Segmentation
  • Supervisor: Nicolas Audebert and Nicolas Thome
• Summer 2019: Research Intern
  • MLIA, LIP6 (Paris)
  • First year of Master Research internship on semantic deep neural networks for Information Retrieval
  • Supervisor: Laure Soulier

Skills

• Deep Learning
  • Computer Vision (Semantic Segmentation, Object detection)
  • Graph Learning (GNN, Recommendation and Dynamic GNN )
• Python
  • Pytorch
  • Graph Library: Pytorch geometric, Neo4J,NetworkX
  • Ultralytics
• Some web skills (scrapping…)

Teaching

Machine learning teacher for the Wagon.

Refresher course in science for the organization AssoFac.

Teaching assistant for the TRIED Master.

Teacher assistant for the MAPSI course (Maths and Applied Statistics for Computer Science).