NeuroVLA: A Brain-inspired Embodied Intelligence for Fluid and Fast Reflexive Robotics Control

cs.RO, cs.AI

Submitted: 2026-01-21

Updated: 2026-10-13

Comments: 14 pages, 8 figures. Added NeuroVLA to the title; clarified language-model design inertia, high-frequency proprioception, motor memory and local feedback; revised biological analogies; corrected figure captions and references. Experimental figures and main quantitative results are unchanged

Code: https://github.com/guoweiyu/NeuroVLA

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

Sources

• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• WorldVLA: Towards Autoregressive Action World Model
• Unified Vision-Language-Action Model
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models

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