collaborators

5 papers

cs.LG2026

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

Lucas Maes, Quentin Le Lidec, Damien Scieur +2

Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces, yet existing methods remain fragile, relying on co…

cs.LG2026

stable-worldmodel: A Platform for Reproducible World Modeling Research and Evaluation

Lucas Maes, Quentin Le Lidec, Luiz Facury +9

World models are central to building agents that can reason, plan, and generalize beyond their training data. However, research on world models is currently fragmented, with dispar…

cs.LG2026

Navigating Potholes with Geometry-Aware Sharpness Minimization

Simon Dufort-Labbé, Mehrab Hamidi, Razvan Pascanu +3

Sharpness-aware minimization (SAM) encourages flat minima by perturbing parameters along directions of high loss curvature, but treats all parameter directions uniformly, ignoring…

cs.AI2026

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

Lucas Maes, Quentin Le Lidec, Dan Haramati +4

World Models have emerged as a powerful paradigm for learning compact, predictive representations of environment dynamics, enabling agents to reason, plan, and generalize beyond di…

cs.LG2025

Understanding Adam Requires Better Rotation Dependent Assumptions

Tianyue H. Zhang, Lucas Maes, Alan Milligan +5

Despite its widespread adoption, Adam's advantage over Stochastic Gradient Descent (SGD) lacks a comprehensive theoretical explanation. This paper investigates Adam's sensitivity t…