Publications

Computer Science

Attentive Perturbation: Extending Prefix Tuning to Large Language Models Inner Representations

From adapters to prefix-tuning, parameter efficient fine-tuning (PEFT) has been a well investigated research field in the past few years, which has led to an entire family of alternative approaches for large language model fine-tuning. All these…

Louis Falissard, Séverine Affeldt, Mohamed Nadif

The 9th International Conference on Machine Learning, Optimization, and Data Science - 2023

Neuroscience

The Arc de Triomphe Construction Test (ATCT): A 1-hour test of executive functions in individuals with traumatic brain injury and radiation-induced leukoencephalopathy

Mateo Campos, Flavie Bompaire, Albane Moreau, Marie Baruteau, Marie de Laage, Christophe Labourdette, Melanie Dandrieux, Laura Terrier, Ioannis Bargiotas, Magali Sallansonnet, Irina Taifas, Marie-Laure Brechemier, Eve Drouard, Camille Tafani, Mona Michaud, Emna Jelili, Pierre-Paul Vidal, Julien Nelson, Nicolas Vayatis, Stéphane Buffat, Damien Ricard

Annals of Physical and Rehabilitation Medicine - 2023

Computer Science

Data Clustering and Representation Learning Based on Networked Data

Abstract To deal simultaneously with both, the attributed network embedding and clustering, we propose a new model exploiting both content and structure information. The proposed model relies on the approximation of the relaxed continuous embedding…

Lazhar Labiod, Mohamed Nadif

The 17th conference of the International Federation of Classification Societies , 2022 - 2023

Neuroscience

Tilt perception is different in the pitch and roll planes in human

Neurophysiological tests probing the vestibulo-ocular, colic and spinal pathways are the gold standard to evaluate the vestibular system in clinics. In contrast, vestibular perception is rarely tested despite its potential usefulness in professional…

Dimitri Keriven Serpollet, David Hartnagel, Yannick James, Stéphane Buffat, Nicolas Vayatis, Ioannis Bargiotas, Pierre‐paul Vidal

Physiological Reports - 2023

Computer Science

Towards a Bi-Stochastic Matrix Approximation of k-means and Some Variants

Abstract The k -means algorithm and some k -means variants have been shown to be useful and effective to tackle the clustering problem. In this paper we embed k -means variants in a bi-stochastic matrix approximation (BMA) framework. Then we derive…

Lazhar Labiod, Mohamed Nadif

The 17th conference of the International Federation of Classification Societies, IFCS 2022 - 2023

Cognitive science

A heartbeat-based study of attention in the detection of digital alarms from focused and distributed supervisory control systems

Frédéric Vanderhaegen, M. Wolff, R. Mollard

Cognition, Technology and Work - 2023

Mathematics

Convergence rates and approximation results for SGD and its continuous-time counterpart

This paper proposes a thorough theoretical analysis of Stochastic Gradient Descent (SGD) with non-increasing step sizes. First, we show that the recursion defining SGD can be provably approximated by solutions of a time inhomogeneous Stochastic…

Xavier Fontaine, Valentin de Bortoli, Alain Durmus

Quantum Physics

Quantum fluctuations induce collective multi-phonons in finite Fermi liquids

We show that collective multi-phonon states in atomic nuclei emerge at high excitation energies when quantum fluctuations are included beyond the independent particle approximation. The quadrupole response of a nucleus is studied using an extension…

Petar Marević, David Regnier, Denis Lacroix

Phys.Rev.C - 2023

Analysis of PDEs

Massively parallel computation of globally optimal shortest paths with curvature penalization

We address the computation of paths globally minimizing an energy involving their curvature, with given endpoints and tangents at these endpoints, according to models known as the Reeds-Shepp car (reversible or forward only), the Euler-Mumford…

Jean-Marie Mirebeau, Lionel Gayraud, Rémi Barrère, Da Chen, François Desquilbet

Concurrency and Computation: Practice and Experience - 2023

Neuroscience

Temporo-basal sulcal connections: a manual annotation protocol and an investigation of sexual dimorphism and heritability

The temporo-basal region of the human brain is composed of the collateral, the occipitotemporal, and the rhinal sulci. We manually rated (using a novel protocol) the connections between rhinal/collateral (RS-CS), collateral/occipito-temporal (CS-OTS…

Kevin de Matos, Claire Cury, Lydia Chougar, Lachlan T Strike, Thibault Rolland, Maximilien Riche, Lisa Hemforth, Alexandre Martin, Tobias Banaschewski, Arun L W Bokde, Sylvane Desrivières, Herta Flor, Antoine Grigis, Hugh Garavan, Penny Gowland, Andreas Heinz, Rüdiger Brühl, Jean-Luc Martinot, Marie-Laure Paillère Martinot, Eric Artiges, Frauke Nees, Juliane H Fröhner, Herve Lemaitre, Dimitri Papadopoulos Orfanos, Tomáš Paus, Luise Poustka, Sarah Hohmann, Sabina Millenet, Juliane H Fröhner, Michael N Smolka, Nilakshi Vaidya, Henrik Walter, Robert Whelan, Gunter Schumann, Vincent Frouin, Meritxell Bach Cuadra, Olivier Colliot, Baptiste Couvy-Duchesne

Brain Structure and Function - 2023