VLA or IL? A Controlled Dataset for Testing Whether Finetuning Turns Your VLA into a Fancy Imitation Learner (opens in new tab)

Motivation Robot manipulation is the ability of a robot to interact with and manipulate objects in the physical world, such as grasping objects, moving them precisely, and adapting to changes in the environment. Traditional approaches such as Imitation Learning (IL) [ACT, Diffusion Policy] learn directly from human demonstrations, mapping visual observations to actions. While effective in controlled settings, these policies are difficult to generalize. Vision-Language-Action (VLA) models [RT-...