Tags / 4 articles
Every article tagged vla, newest first.
With no real robot data, only simulated demos, MolmoBot doubles the real-world success of a policy trained on 10,000+ hours of real robot data.
sim-to-realsimulationimitation-learningvla
Both look at a camera image, read an instruction and output robot moves. A VLA starts from an image-and-text model and learns the moves. A WAM starts from a video model and also learns the frames that come next. Eight drawings on what that changes.
world-action-modelsvlaroboticsmachine-learning
Keep every stream, compress it as you go, and learn what to remember.
robot-memoryvla
Many robot policies decide from the last few frames. A snapshot of six ways to give them memory in October 2026, what each one stores, and what has been measured.
robot-memorylong-horizonnavigationvla