3 papers
cs.CV2026
CLIMB: Centroid-Based Hierarchical Memory for Online Continual Self-Supervised Learning
Julien Lefebvre, Stefan Duffner, Mathieu Lefort
Online Continual Self-Supervised Learning (OCSSL) aims to learn representations from a continuous stream of unlabeled data, without knowledge of task boundaries and under memory co…
cs.AI2026
Exploration and Online Transfer with Behavioral Foundation Models
Louis Bagot, Mathieu Lefort, Laëtitia Matignon
Zero-shot Transfer in Reinforcement Learning (RL) aims to train an agent that can generate optimal policies for any reward function, without additional learning at transfer time, w…
cs.CV2026
XmoPipe: A Pipeline for Large-Scale In-the-Wild Human Motion Dataset Construction
Nathan Salazar, Emmanuel Dellandréa, Mathieu Lefort +1
Large-scale human motion datasets are essential for training robust motion models for analysis, synthesis, and understanding. While marker-based motion capture provides precise dat…