About me
I am an Assistant Professor in the Data Science department of EURECOM. I build probabilistic methods that let machines perceive and reason about the world under uncertainty, at the meeting point of generative modelling and information theory. My work spans continuous-time, functional and infinite-dimensional diffusion processes — introduced with Continuous-Time Functional Diffusion Processes (NeurIPS 2023) and surveyed in Generative Diffusion Models in Infinite Dimensions (Philosophical Transactions of the Royal Society A, 2025) — as well as multimodal and discrete generative models.
My group develops diffusion-based estimators that make classically intractable information-theoretic quantities measurable at scale: MINDE set the state of the art for neural mutual-information estimation (ICLR 2024), SΩI was the first scalable estimator of O-information beyond Gaussian systems (ICML 2024), TENDE set the state of the art for transfer entropy (AISTATS 2026), INFO-SEDD (ICLR 2026) brought this programme to discrete data with continuous-time Markov chains, outperforming embedding-based neural estimators, and DIPHINE is the first neural estimator of integrated information decomposition (Φ-ID).
Two current efforts: trajectory inference — recovering latent dynamics from snapshot data — where our relative-entropy estimation framework in function space appears at ICML 2026; and, separately, foundation models for trajectory inference, which is ongoing work.
I publish regularly in the main tracks of ICML, ICLR, NeurIPS and AISTATS. I am P.I. (EURECOM) of the ANR project Gen-T, co-P.I. of P-AI-LOT (industrial chair on agentic LLMs, with Amadeus) and of European and industrial projects on machine perception with partners including Huawei Technologies; industrial patents filed with Renault. ELLIS member.
I received my M.Sc. (2016) and Ph.D. (2021) from Politecnico di Torino in Electronic and Telecommunications Engineering. Before EURECOM I worked on statistical signal processing for satellite navigation systems. Here is my full CV.
Contact
Campus SophiaTech: 450, route des Chappes – 06410 BIOT (CS 50193 – 06904 Sophia Antipolis cedex)
Tel: +33 (0)4 93 00 81 45
giulio.franzese[AT]eurecom.fr
