Guillaume Sartoretti

Predicting compact, learned future representations for world-action modeling slashes training costs by 65x and outperforms native visual targets, even with smaller models.

Perceptive General Motion Tracking pipeline for humanoid robots that learns terrain adaptation from independently selected motion references and terrains, providing a unified policy for terrain-adaptive locomotion, diverse whole-body behaviors, and teleoperation in complex environments.

Planner-Conditioned Diffusion Policy enables agents to generate diverse, non-redundant trajectories, achieving perfect success rates while enhancing travel efficiency and coordination.

SJRL not only overcomes collision challenges in multi-agent navigation but also adapts dynamically to real-world constraints, outperforming traditional methods in complex environments.

PRIMAL3 achieves unprecedented scalability in multi-agent pathfinding, successfully coordinating 100,000 agents while navigating complex environments.