LinhanWangother

GlanceWAM reproduction bundle

A reproduction bundle for GlanceWAM (Sparse Test-Time Imagination for World-Action Models) containing pre-trained checkpoints, datasets, and code for evaluating world-action models on LIBERO and RoboCasa kitchen benchmarks.

Downloads12
Episodes4000
Likes1

Why This Matters for Physical AI

This dataset is critical for advancing world-action models by providing benchmark evaluations on real robot manipulation tasks with vision-language grounding, demonstrating how sparse test-time imagination can improve policy learning efficiency.

Technical Profile

Modalities
rgblanguage
Robot Embodiments
mobile_manipulator
Action Space
end_effector_delta
Environment
kitchensimulation
Task Types
manipulationpick_and_place
Episodes
4000
Data Format
LeRobot
Annotation Types
language_instructionsaction_labels
License
other
Part of the GlanceWAM family

Access

Need custom rgb data?

Claru builds purpose-built datasets for kitchen applications with dense human annotations and quality assurance.

Request a Sample Pack

Related Datasets