CALICE accepted in ACM TOMM
Our paper “CALICE: Continuous bitrate control with Adapted LIC modEl” was accepted in ACM Transactions on Multimedia Computing, Communications, and Applications.
Assistant Professor at Télécom Paris, Institut Polytechnique de Paris
I am an Assistant Professor in Machine Learning and Computer Vision at Télécom Paris, Institut Polytechnique de Paris. I work in the Information Processing and Communications Laboratory (LTCI), within the Multimedia team, and I am a member of the ELLIS Society.
My research focuses on machine learning and signal processing for relational data, including graphs and higher-order structures. I am also interested in applications in computer vision, circuit design, environmental monitoring, materials analysis, physical systems, and underwater acoustics.
I received my PhD in Applied Mathematics from La Rochelle Université in 2022. Before my doctoral studies, I worked on graph signal processing at the University of Delaware and completed my MSc and BSc degrees at Universidad de Antioquia, Colombia.
Our paper “CALICE: Continuous bitrate control with Adapted LIC modEl” was accepted in ACM Transactions on Multimedia Computing, Communications, and Applications.
I was selected as an ICML 2026 Gold Reviewer, recognizing the top 25% of reviewers.
The papers study feature-aware hypergraph generation and graph-informed flow matching for spatiotemporal imputation.
The teaching area is designed as a course library: web-based lecture notes, references, exercises, and slides.
Lecture 6 · Graph generation. Properties of real-world graphs; Erdos-Renyi random graphs; deep generative models; GraphRNN; iterative local expansion by coarsening.
Also online: Lecture 3 · Scaling up graph neural networks, Lecture 4 · Spatiotemporal analysis with graphs, Lecture 5 · Recommender systems, and 2 more.