ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play Adaptation

arXiv:2605.30484 · cs.RO · Submitted 2026-05-28 · Read on arXiv

cs.RO

Submitted: 2026-05-28

Updated: 2026-10-18

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Decoder — 2× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 5 episodes

Sources

• RT-1: Robotics Transformer for Real-World Control at Scale
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• A Survey on Vision-Language-Action Models: An Action Tokenization Perspective
• Survey of Vision-Language-Action Models for Embodied Manipulation
• WorldVLA: Towards Autoregressive Action World Model
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulation
• Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation
• Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better
• UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
• ControlVLA: Few-shot Object-centric Adaptation for Pre-trained Vision-Language-Action Models
• GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization
• BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
• Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
• FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Model
• RynnVLA-001: Using Human Demonstrations to Improve Robot Manipulation
• PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies