2026
Align-Then-stEer: Adapting the Vision-Language Action Models through Unified Latent Guidance
ICLR 2026poster
Vision-Language-Action (VLA) models pre-trained on large, diverse datasets show remarkable potential for general-purpose robotic manipulation. However, a primary bottleneck remains in adapting these models to downstream tasks, especially when the robot's embodiment or the task itself differs from th…