Tae-Won Lee

Toward Human Preference Optimization for Vision-Language-Action Models: A Pilot Study on the Limits of Imitation Learning

Vision-Language-Action (VLA) models trained via imitation learning have achieved impressive results on robotic manipulation, yet their performance degrades significantly on complex, multi-step tasks. We evaluate NVIDIA GR00T N1.6, a state-of-the-art cross-embodiment VLA model (~1.09B parameters), on…