Latest news

[Nov 26] Recognized as a Top Area Chair at NeurIPS 2026.

[Sep 26] Three papers accepted at NeurIPS 2026:

  • Decoupled Mode Connectivity for Base-to-Novel Generalization in Vision-Language Models;
  • Uncertainty is an Underconstrained Axis in Lossy Compression;
  • SOLA: A Structured Operator Library for Attention in Pretrained Vision Transformers.

[Aug 26] Article accepted for publication at the IEEE Transactions on Multimedia: Distilling Learned Image Compression Models: An Analytical Approach for Low-Latency FPGA Deployment Alaa Eddine Mazouz, Sumanta Chaudhuri, Marco Cagnazzo, Mihai Mitrea, Enzo Tartaglione, Bruno Zatt, Attilio Fiandrotti

[Jun 26] Article accepted for publication at the 19th European Conference on Computer Vision (ECCV): AracNet: Revealing Debiasing Signals across Layers with Shallow Monitors Vito Paolo Pastore, Massimiliano Ciranni, Enzo Tartaglione, Vittorio Murino

[Jun 26] Article accepted for publication at the ACM Transactions on Multimedia Computing, Communications, and Applications: CALICE: Continuous Bitrate Control with Adapted LIC Model Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo, Attilio Fiandrotti, Marco Grangetto, Enzo Tartaglione

[Jun 26] Article accepted for publication at IEEE Transactions on Multimedia: Security and Real-time FPGA integration for Learned Image Compression Mazouz Alaa Eddine, Sumanta Chaudhuri, Marco Cagnazzo, Mihai Mitrea, Enzo Tartaglione, Attilio Fiandrotti

Professorships, PhDs and stages applications are now open!

See the current openings


Mission

In a world where deep learning is becoming more and more state-of-the-art, where the race to computational capabilities determines new technologies, it is important to open the black box that deep learning is. Many researchers are already taking important steps in this direction, despite the wide range of scientific backgrounds. This is good, this is progress!

We target it in the long term, developing techniques that simplify these models. Some are easier to prune than others: why? How is information being processed inside a deep model from a macroscopic perspective? These are a few of the questions to be answered to move in the right direction.

An interactive map of all my papers, grouped by research theme.

Open the research graph

Currently working with

PhD student

Dorian Gailhard

Dorian Gailhard

PhD student
Generative models and Graph Neural Networks for SoCs
Co-supervised with Jhony H. Giraldo
Ivan Luiz De Moura Matos

Ivan Luiz De Moura Matos

PhD student
Debiasing through NAS
Previously: Stage M2 Oct 23 to Feb 24
Kian Bakhtari

Kian Bakhtari

PhD student
Efficient foundation models exploitation for autonomous driving
Co-supervised with Stephan Alaniz
Leonardo Magliolo

Leonardo Magliolo

PhD student
Information flow in Deep Neural Networks
Lê Trung Nguyen

Lê Trung Nguyen

PhD student
Methods for on-device training
Co-supervised with Van-Tam Nguyen
Rayyan Ahmed

Rayyan Ahmed

PhD student
Explaining and Removing Social Biases in Text-to-Image Generative AI
Co-supervised with Stephan Alaniz
Salaheldin Mohamed

Salaheldin Mohamed

PhD student
Co-supervised with Kaouther Messaoud
Yinghao Wang

Yinghao Wang

PhD student
Foundation models for EEG treatment
Co-supervised with Van-Tam Nguyen
Zhu Liao

Zhu Liao

PhD student
Deep Neural Network pruning
Co-supervised with Van-Tam Nguyen

Formerly advising

PostDoc

Research Engineer

PhD student

Invited PhD student

Research path student

PRIM project

Stage M2

Stage M1

Free stage