Latest news

Paper accepted for publication at DCC 2024 as oral - Domain Adaptation for learned image compression with supervised Adapters

Mission

In a world where deep learning is becoming more and more state-of-the-art, where the race to the computational capabilities determines the new technologies, it is crucial to open the black box deep learning is. Many good-willing researchers are already moving important steps in such direction, despite a wide multitiude and hetereogeneity of scientific backgrounds. This is good, this is progress!
We target it in the long term developing techniques which simplify these models. Some are easier to prune than others: why? How is the information being processed inside a deep model, from a macroscopic perspective? These are few of the questions to be answered to move in the right direction!

Green AI

Remotion of unnecessary neurons and/or synapses towards reduction of power consumption.

Model debiasing

Understand biases in data and cure the trained model.

Privacy in AI

Guaranteeing privacy in AI will be an important theme in the next years.

Understand the information flow

Modeling how the information is processed in deep models is our final goal.

Currently working with

Giommaria Pilo

Research Engineer
Deployment of frugal and efficient AI at the edge

Imad Eddine Marouf

PhD student
Efficient transformers for computer vision
Previously: Stage M2 Feb-Sep 2022

Victor Quétu

PhD student
Regularization for deep learning

Melan Vijayaratnam

PhD student
Zero-latency video prediction

Rémi Nahon

PhD student
Debiasing in Deep neural networks
(Memory and energy efficient AI)

Yinghao Wang

PhD student
Neural Architecture Search approaches
(AIoT and neurofeedback for cognitive training acceleration)

Zhu Liao

PhD student
Material accelerator for AIoT

Aël Quélennec

PhD student
On-device learning

Gabriele Spadaro

PhD student
Compression with Graph Neural Networks
Co-tutelle with University of Turin, Italy

Carl De Sousa Trias

PhD student
Watermarking deep models
(Informal advising, funded within the project NewEMMA)

Muhammad Ali Salman

Visiting PhD student (Feb - Jul 2024)
Compression with deep neural networks

Maxime Girard

Research path student (co-encadrement)
Attention state detection through EEG signals

Roan Rubiales

Research path student (co-encadrement)
Efficient deep learning at the edge

Lê Trung Nguyen

Stage M2
Methods for on-device training

Nour Hezbri

Stagiaire (Mar - Aug 2024)
Compression with artificial neural networks

Formerly advising