LIBERO-Plus

'LIBERO-plus' is a dataset/benchmark that contains a diverse set of robotic manipulation tasks used to evaluate the performance and generalization capabilities of vision-language-action models.

Papers using LIBERO-Plus (6)

VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model2026Reflective VLA: In-Context Action Consequences Make VLAs Generalize2026TAG: Target-Agnostic Guidance for Stable Object-Centric Inference in Vision-Language-Action Models2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Prior2026JEPA-VLA: Video Predictive Embedding is Needed for VLA Models2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Models2026