LIBERO

LIBERO is a simulation benchmark used to evaluate Vision-Language-Action (VLA) models by assessing their performance in transferring semantic knowledge to physical robotic control.

Papers using LIBERO (28)

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning2025 · 83 citesStarvla-\(\alpha\): Reducing Complexity In Vision-language-action Systems2026Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?2026Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies2026CLAP: Direct VLM-to-VLA Adaptation via Language-Action Grounding2026VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment2026WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling2026Teaching Tiny VLA Models Where to Look and How to Move2026TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging2026GEAR-VLA: Learning Geometry-Aware Action Representations for Generalizable Robotic Manipulation2026Agentic-VLA: Efficient Online Adaptation for Vision-Language-Action Models2026{\Omega}-QVLA: Robust Quantization for Vision-Language-Action Models via Composite Rotation and Per-step Scaling2026PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space2026MIRTH: Mutual-Information Reasoning with Temporal Hubs for Vision-Language-Action Agents2026ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation2026Key-Gram: Extensible World Knowledge for Embodied Manipulation2026DyGRO-VLA: Cross-Task Scaling of Vision-Language-Action Models via Dynamic Grouped Residual Optimization2026HELM: Harness-enhanced Long-horizon Memory For Vision-language-action Manipulation2026Restoring Linguistic Grounding in VLA Models via Train-Free Attention Recalibration2026VLA-Thinker: Boosting Vision-Language-Action Models through Thinking-with-Image Reasoning2026FUTURE-VLA: Forecasting Unified Trajectories Under Real-time Execution2026CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion2026Demonstration-Free Robotic Control via LLM Agents2026Continually Evolving Skill Knowledge In Vision Language Action Model2025MetaVLA: Unified Meta Co-training For Efficient Embodied Adaption2025SpecPrune-VLA: Accelerating Vision-Language-Action Models via Action-Aware Self-Speculative Pruning2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies2025