LIBERO-10

LIBERO-10 is a benchmark dataset used to evaluate the performance of Vision-Language-Action models in robotic manipulation tasks.

Papers using LIBERO-10 (2)

$\pi_0$-EqM: Equilibrium Matching for Closed-Loop Vision-Language-Action Control2026Sparse2Act: Learning Action-Aligned Sparse 3D Representations for Cross-Domain Robot Manipulation2026