Thesis defence and HDR

The defense will be held in French and will be followed by a reception in the showroom space of the MJK.

Process-aware attack detection in industrial control systems using explianable artificial intelligence

Augmented Reality for Surgery: From Physical to Virtual Guidance in Arthroscopy

On the Fragility of Fairness in Recommender Systems: From Fairness Optimization to Fairness Manipulation

The Geometry of Strategic Competition: Recurrent Dynamics and Adaptive Learning in Games

Efficient Self-Supervised Learning for Speech Processing

Stochastic Optimization Algorithms in Machine Learning: Dynamics, Convergence, Generalization

Resource-Efficient Deep Learning: Advances in Model Compression and Geometric Semi-Supervised Learning

Coreference Resolution into Machine Translation

Towards practical performance anomaly detection in microservice applications

High Performance Online Deep Neural Network Training from Synthetic Data with Active Learning for Scientific Computing (or: "How to train neural networks to model physical systems accurately — through smarter data, not more compute?")

Multi-Resident Data Association in Smart Homes: Modeling and Learning

CIFRE Ph.D : Methodology for Reusing Deep Learning Models (Bootstrapping Deep Learning Journeys)

Multimodal Group Emotion Recognition In-the-Wild: Towards a Privacy-Safe Non-Individual Approach

Quantized DNN learning algorithms with limited hardware overhead for Edge implementation

Advanced Early Fusion Approaches for Multimodal Image Fusion for Pedestrian and Vehicle Detection