Publications

Publications of Giulio Franzese (EURECOM): diffusion models, information-theoretic estimation, trajectory inference. Generated from the same bibliography as the CV.

My work sits at the meeting point of generative modelling and information theory: diffusion processes in continuous time and in function space, multimodal and discrete generative models, diffusion-based estimators of information-theoretic quantities, and, most recently, trajectory inference and foundation models for it.

This list is generated from the same bibliography as my CV. Also on Google Scholar, DBLP and the EURECOM publication database.

2026

A. Foresti, M. Bounoua, G. Franzese, L. Ambrogioni, and P. Michiardi. Improved Sampling Schedules for Discrete Diffusion Models. arXiv preprint, 2026. arXiv:2602.06849
A. Foresti, G. Franzese, and P. Michiardi. Information Estimation with Discrete Diffusion. The Fourteenth International Conference on Learning Representations (ICLR), 2026. arXiv:2502.19183 Preprint circulated as “INFO-SEDD: Continuous Time Markov Chains as Scalable Information Metrics Estimators”
C. Wang, L. Nepote, G. Franzese, and P. Michiardi. Relative Entropy Estimation in Function Space: Theory and Applications to Trajectory Inference. 43rd International Conference on Machine Learning (ICML), 2026. arXiv:2604.20775
A. Foresti, I. Butakov, A. Tolmachev, G. Franzese, A. Frolov, and P. Michiardi. Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation. arXiv preprint, 2026. arXiv:2607.03487
S. P. Galeano Muñoz, M. Bounoua, G. Franzese, P. Michiardi, and M. Filippone. DIPHINE: Diffusion-based Φ-ID Neural Estimator. arXiv preprint, 2026. arXiv:2606.18997
S. P. Galeano Muñoz, M. Bounoua, G. Franzese, P. Michiardi, and M. Filippone. TENDE: Transfer Entropy Neural Diffusion Estimation. 29th International Conference on Artificial Intelligence and Statistics (AISTATS), 2026. arXiv:2510.14096

2025

G. Franzese and P. Michiardi. Generative diffusion models in infinite dimensions: a survey. Philosophical Transactions A, 383(2299), 2025.
S. Clemente, Z. Ben Houidi, A. Huet, D. Rossi, G. Franzese, and P. Michiardi. In Praise of Stubbornness: The Case for Cognitive-Dissonance-Aware Knowledge Updates in LLMs. arXiv preprint, 2025. arXiv:2502.04390
C. Wang, G. Franzese, A. Finamore, M. Gallo, and P. Michiardi. Information Theoretic Text-to-Image Alignment. The Thirteenth International Conference on Learning Representations, 2025.
G. Franzese, M. Martini, G. Corallo, P. Papotti, and P. Michiardi. Latent Abstractions in Generative Diffusion Models. Entropy, 27(4), 2025.
M. Bounoua, G. Franzese, and P. Michiardi. Learning to Match Unpaired Data with Minimum Entropy Coupling. Forty-second International Conference on Machine Learning, 2025.
M. Rosso, S. Rossi, G. Franzese, M. Heinonen, and M. Filippone. Scaling Laws for Uncertainty in Deep Learning. arXiv preprint, 2025. arXiv:2506.09648
C. Wang, G. Franzese, A. Finamore, and P. Michiardi. RFMI: Estimating Mutual Information on Rectified Flow for Text-to-Image Alignment. ICLR 2025 Workshop on Deep Generative Model in Machine Learning: Theory, Principle and Efficacy, 2025.

2024

G. Di Giacomo, G. Franzese, T. Cerquitelli, C. Chiasserini, and P. Michiardi. DiMViDA: Diffusion-Based Multi-View Data Augmentation. 2024 IEEE 29th International Workshop on Computer Aided Modeling and Design of Communication Links and Networks (CAMAD), 2024.
M. Bounoua, G. Franzese, and P. Michiardi. Multi-modal latent diffusion. Entropy, 26(4), 2024.
G. Di Giacomo, G. Franzese, T. Cerquitelli, C. F. Chiasserini, and P. Michiardi. DiMViS: Diffusion-Based Multi-View Synthesis. ICML 2024 Workshop on Structured Probabilistic Inference & Generative Modeling, 2024.
G. Franzese, M. Bounoua, and P. Michiardi. MINDE: Mutual Information Neural Diffusion Estimation. The Twelfth International Conference on Learning Representations, 2024.
M. Bounoua, G. Franzese, and P. Michiardi. SΩI: Score-based O-INFORMATION Estimation. ICML 2024, 41st International Conference on Machine Learning, 2024.

2023

G. Franzese, G. Corallo, S. Rossi, M. Heinonen, M. Filippone, and P. Michiardi. Continuous-Time Functional Diffusion Processes. 37th Conference on Neural Information Processing Systems, NeurIPS 2023, 2023. arXiv:2303.00800
G. Franzese, S. Rossi, L. Yang, A. Finamore, D. Rossi, M. Filippone, and P. Michiardi. How much is enough? a study on diffusion times in score-based generative models. Entropy, 25(4), 2023.
B.-H. Tran, G. Franzese, P. Michiardi, and M. Filippone. Improving Training of Likelihood-based Generative Models with Gaussian Homotopy. SPIGM 2023, 1st Workshop on Structured Probabilistic Inference & Generative Modeling, co-located with ICML 2023, 2023.
M. Bounoua, G. Franzese, and P. Michiardi. Masked Multi-time Diffusion for Multi-modal Generative Modeling. NeurIPS 2023 Workshop on Diffusion Models, 2023.
G. Di Giacomo, G. Franzese, T. Cerquitelli, C.-F. Chiasserini, and P. Michiardi. Multi-View Latent Diffusion. 2023 IEEE International Conference on Big Data (BigData), 2023.
B.-H. Tran, G. Franzese, P. Michiardi, and M. Filippone. One-line-of-code data mollification improves optimization of likelihood-based generative models. Advances in Neural Information Processing Systems, 36, 2023.

2022

G. Franzese, S. Rossi, L. Yang, A. Finamore, D. Rossi, M. Filippone, and P. Michiardi. A New Look on Diffusion Times for Score-based Generative Models. ICML 2022, 39th International Conference on Machine Learning, Continuous time methods for machine learning Workshop, 2022.
G. Franzese, D. Milios, M. Filippone, and P. Michiardi. Revisiting the Effects of Stochasticity for Hamiltonian Samplers. Proceedings of the 39th International Conference on Machine Learning, 2022.

2021

G. Franzese, D. Milios, M. Filippone, and P. Michiardi. A scalable bayesian sampling method based on stochastic gradient descent isotropization. Entropy, 23(11), 2021.
G. Franzese. Contributions to Efficient Machine Learning. PhD thesis, Politecnico di Torino, 2021.
G. Franzese, Y. Yan, G. Serra, I. D’Onofrio, R. Appuswamy, and P. Michiardi. Generative dna: Representation learning for dna-based approximate image storage. 2021 International Conference on Visual Communications and Image Processing (VCIP), 2021.

2020

G. Franzese and M. Visintin. Probabilistic ensemble of deep information networks. Entropy, 22(1), 2020.
G. Franzese, N. Linty, and F. Dovis. Semi-supervised GNSS scintillations detection based on DeepInfomax. Applied Sciences, 10(1), 2020.

2019

R. Candela, G. Franzese, M. Filippone, and P. Michiardi. Sparsification as a Remedy for Staleness in Distributed Asynchronous SGD. arXiv preprint, 2019. arXiv:1910.09466

2018

G. Franzese and M. Visintin. Deep Information Networks. arXiv preprint, 2018. arXiv:1803.02251

2017

G. Franzese, L. Lo Presti, and I. Martini. A novel Markov model for the computation of the Continuity Risk in maritime applications. Proceedings of the 2017 International Technical Meeting of The Institute of Navigation, 2017.

2014

S. Ugazio, G. Franzese, L. Lo Presti et al. LOS/NLOS detection combining adaptive filtering and channel propagation model. Satellite Navigation Technologies and European Workshop on GNSS Signals and Signal Processing (NAVITEC), 2014 7th ESA Workshop on, 2014.