Équipe de recherche :Research Team:
Multimédia (MM)Multimedia (MM)
Laboratoire :Laboratory:
Laboratoire Traitement et Communication de l'Information (LTCI)Information Processing and Communication Laboratory (LTCI)
Département :Department:
Image, Données, Signal (IDS)Image, Data, Signal (IDS)
Jhony H. Giraldo is an Assistant Professor at Télécom Paris , Institut Polytechnique de Paris, working in the Information Processing and Communications Laboratory (LTCI) in the Multimedia team. He is a member of the ELLIS Society.
He received his Ph.D. in Applied Mathematics from La Rochelle Université (Laboratoire MIA – Mathématiques, Image et Applications) in 2022. During his Ph.D., he was a visiting researcher at the Centre de Vision Numérique (CVN) and Inria OPIS, CentraleSupélec, Université Paris-Saclay (2022), and at the CVPR Lab, Università degli Studi di Napoli Parthenope, Italy (2021).
Before his doctoral studies, he worked as a Research Assistant at the University of Delaware, USA (2018–2019), focusing on Graph Signal Processing. He holds both a Master’s degree (with honors, 2018) and a Bachelor’s degree in Electronics Engineering (2016) from Universidad de Antioquia, Colombia.
His research focuses on the theory and applications of Geometric Deep Learning (graph and higher-order networks), Computer Vision, Machine Learning, and Graph Signal Processing.
Research activities :
Graphs
- Theory of Graph Neural Networks (GNNs): Over-smoothing, Over-squashing, Generalization
- Scaling Up GNNs
- Spatiotemporal Analysis: Imputation and Forecasting of Time Series on Graphs
- Continuous GNNs
- Self-Supervised Learning on Graphs
Computer Vision
- GNNs for Vision Tasks
- Foundation Models in Biodiversity Monitoring
- Generative Modeling in Vision
Higher-order Structures:
- Hypergraph Generation
- Simplicial Neural Networks
- Cellular Neural Networks
- Continous Higher-order Neural Networks
Fundings:
Agence Nationale de la Recherche (ANR) Project JCJC DeSNAP
- “Deep Simplicial Neural Networks for Advanced Geometry Processing”
Role: PI. Duration: 2025–2029
Hi! Paris Funding:
- Host Hi! Paris International Visiting Professor (Antonio Ortega), 2026-2029
- Supervisor Hi! Paris Postdoc Fellowship (Aref Einizade), 2023-2025.
- Supervisor Hi! Paris Half PhD Funding (Antoine Vialle), 2025-2028.
NVIDIA Academic Grant Program Award (GPU hours)
- “Bridging the Gap between Foundation Models and Camera Trap Image Recognition”
Role: PI. Duration: January 2025 – June 2025
Agence Nationale de la Recherche (ANR) Project SODA
- “System On Chip Design leveraging Artificial Intelligence”
Role: Team Member. Duration: 2023–2027
Teaching activities :
- Machine Learning with Graphs
- Deep Learning for Computer Vision
