Lucas Maes

According to our database, Lucas Maes authored at least 7 papers between 2023 and 2026.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2026

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels.

Lucas Maes, Quentin Le Lidec, Damien Scieur, Yann LeCun, Randall Balestriero

CoRR, March, 2026

Causal-JEPA: Learning World Models through Object-Level Latent Interventions.

Heejeong Nam, Quentin Le Lidec, Lucas Maes, Yann LeCun, Randall Balestriero

CoRR, February, 2026

stable-worldmodel-v1: Reproducible World Modeling Research and Evaluation.

Lucas Maes, Quentin Le Lidec, Dan Haramati, Nassim Massaudi, Damien Scieur, Yann LeCun, Randall Balestriero

CoRR, February, 2026

2025

stable-pretraining-v1: Foundation Model Research Made Simple.

Randall Balestriero, Hugues Van Assel, Sami BuGhanem, Lucas Maes

CoRR, November, 2025

On the Importance of Embedding Norms in Self-Supervised Learning.

Andrew Draganov, Sharvaree Vadgama, Sebastian Damrich, Jan Niklas Böhm, Lucas Maes, Dmitry Kobak, Erik J. Bekkers

Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024

Understanding Adam Requires Better Rotation Dependent Assumptions.

Lucas Maes, Tianyue H. Zhang, Alexia Jolicoeur-Martineau, Ioannis Mitliagkas, Damien Scieur, Simon Lacoste-Julien, Charles Guille-Escuret

CoRR, 2024

2023

Unity is Strength: Cross-Task Knowledge Distillation to Improve Code Review Generation.

Oussama Ben Sghaier, Lucas Maes, Houari A. Sahraoui

CoRR, 2023