LIBERO-Long

The 'LIBERO-LONG' dataset/benchmark contains data for evaluating robotic manipulation tasks, specifically focusing on the effectiveness of planning frameworks like CLaD in achieving successful kinematic and semantic transitions.

Papers using LIBERO-Long (11)

Drift is a Sampling Error: SNR-Aware Power Distributions for Long-Horizon Robotic Planning2026Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models2026Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation2026AtomicVLA: Unlocking the Potential of Atomic Skill Learning in Robots2026CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics2026MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction2026LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulation2026HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Models2025Eva-VLA: Evaluating Vision-Language-Action Models' Robustness Under Real-World Physical Variations2025LaDi-WM: A Latent Diffusion-based World Model for Predictive Manipulation2025