Jhony H. Giraldo

Assistant Professor at Télécom Paris, Institut Polytechnique de Paris

prof_pic.jpg

Office 5D24

19 place Marguerite Perey

91120 Palaiseau, France

I am an Assistant Professor at Télécom Paris, Institut Polytechnique de Paris, working in the Information Processing and Communications Laboratory (LTCI) in the Multimedia team. I’m a member of the ELLIS Society and the IEEE Signal Processing Society.

My research focuses on the theory and applications of Geometric Deep Learning (graph and higher-order networks), Computer Vision, Machine Learning, and Graph Signal Processing.

I received my Ph.D. in Applied Mathematics from La Rochelle Université (Laboratoire MIA – Mathématiques, Image et Applications) in 2022. During my Ph.D., I 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 my doctoral studies, I worked as a Research Assistant at the University of Delaware, USA (2018–2019), focusing on Graph Signal Processing. I hold both a Master’s degree (with honors, 2018) and a Bachelor’s degree in Electronics Engineering (2016) from Universidad de Antioquia, Colombia.

📢 Call for Postdoc: I am looking for postdoc interested in geometric deep learning starting in spring/summer 2026. More information: Full postdoc call

📢 Call for PhD student: We’re looking for PhD student in Compression and Efficient Processing of Graph Data: From Signal Processing to Deep Learning starting in Fall 2026. More information: Full PhD call

📢 Call for Internships 2025-2026: I am looking for motivated students interested in geometric deep learning for internships starting in spring 2026.

🎓 For M1 and M2 students at IP Paris: I am happy to supervise a limited number of master’s projects. Please note that I expect you to be enrolled in my course Machine Learning with Graphs (APM_5DS30_TP).

News

Jan 22, 2026 Our paper “Generalization Bounds for Spectral GNNs via Fourier Domain Analysis” was accepted at AISTATS 2026!
Jan 03, 2026 Our paper “WildIng: A Wildlife Image Invariant Representation Model for Geographical Domain Shift” was accepted at the International Journal of Computer Vision!
Nov 26, 2025 Our paper “TEP-ones: A simple yet effective approach for transferability estimation of pruned backbones” was accepted at Neurocomputing!
Nov 16, 2025 We have four papers accepted at NeurIPS 2025 (one in the main track and three workshops)! The papers cover: simplicial neural networks, tensorial PDEs on graphs, material science with geometric graph neural networks, and graphs for environmental applications.
Sep 19, 2025 I’ve become ELLIS (European Laboratory for Learning and Intelligent Systems) member!