Randall Balestriero

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

arXiv 2026

Causal-JEPA: Learning World Models through Object-Level Latent Masking

arXiv 2026

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

arXiv 2026

stable-pretraining-v1: Foundation Model Research Made Simple

arXiv 2025

LeJEPA: Provable and Scalable Self-Supervised Learning Without the Heuristics

arXiv 2025

UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling

arXiv 2024

Deep Networks Always Grok and Here is Why

arXiv 2024

SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries

CVPR 2023 1

Max-Affine Spline Insights Into Deep Network Pruning

max-affine-spline-insights-into-deep-network

Lucas Maes

Yann LeCun

VP & Chief AI Scientist

Quentin Le Lidec

Richard Baraniuk

Ahmed Imtiaz Humayun

Damien Scieur

Caner Hazirbas

Dan Haramati

Diane Bouchacourt

Guha Balakrishnan