Kimin Lee

Achieving a near-perfect alignment with real-world robot evaluations, RoboWorld redefines how we assess generalist robot policies in simulated environments.

Training robots on human-present data leads to significantly improved human-aware behaviors, highlighting the critical role of human interaction in robotic learning.

SPACE enables robots to learn from cross-robot data, achieving superior generalization and adaptability in diverse operational contexts.

Mistakes in human demonstrations can enhance robot learning when properly harnessed, revealing a new dimension of value estimation that traditional methods overlook.

Robots can now interpret nonverbal cues alongside verbal instructions, drastically reducing the effort required from users to convey intent.