activity
20242026
collaborators

6 papers

cs.LG2026

Batch Normalization for Neural Networks on Complex Domains

Xuan Son Nguyen, Nistor Grozavu

Riemannian neural networks have proven effective in solving a variety of machine learning tasks. The key to their success lies in the development of principled Riemannian analogs o…

cs.AR2025

Coliseum project: Correlating climate change data with the behavior of heritage materials

A Cormier, David Roqui, Fabrice Surma +5

Heritage materials are already affected by climate change, and increasing climatic variations reduces the lifespan of monuments. As weathering depends on many factors, it is also d…

stat.ML2025

Siegel Neural Networks

Xuan Son Nguyen, Aymeric Histace, Nistor Grozavu

Riemannian symmetric spaces (RSS) such as hyperbolic spaces and symmetric positive definite (SPD) manifolds have become popular spaces for representation learning. In this paper, w…

cs.AI2025

A Multimodal Approach to Heritage Preservation in the Context of Climate Change

David Roqui, Adèle Cormier, nistor Grozavu +1

Cultural heritage sites face accelerating degradation due to climate change, yet tradi- tional monitoring relies on unimodal analysis (visual inspection or environmental sen- sors…

cs.IR2024

CADMR: Cross-Attention and Disentangled Learning for Multimodal Recommender Systems

Yasser Khalafaoui, Martino Lovisetto, Basarab Matei +1

The increasing availability and diversity of multimodal data in recommender systems offer new avenues for enhancing recommendation accuracy and user satisfaction. However, these sy…

stat.ML2024

Deep Matrix Factorization with Adaptive Weights for Multi-View Clustering

Yasser Khalafaoui, Basarab Matei, Martino Lovisetto +1

Recently, deep matrix factorization has been established as a powerful model for unsupervised tasks, achieving promising results, especially for multi-view clustering. However, exi…