Beyond Token Importance: Preserving Spatial Scaffolds for Efficient Vision-Language-Action Inference

arXiv:2609.36967 · cs.RO · Submitted 2026-09-29 · Read on arXiv

cs.RO

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Pruning — 148× in this paper · explained in 4 episodes
• Transformer — 5× in this paper · explained in 2 episodes
• Benchmark — 4× in this paper · explained in 2 episodes
• Foundation Model — 3× in this paper · explained in 3 episodes
• Vision-Language-Action (VLA) Models — 3× in this paper · explained in 2 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Ablation Studies — 1× in this paper · explained in 1 episode
• Action Decoder — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Allocator — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Embodied AI — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Pairwise Comparisons — 1× in this paper · explained in 2 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RT-1: Robotics Transformer for Real-World Control at Scale
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
• Fast-in-Slow: A Dual-System Foundation Model Unifying Fast Manipulation within Slow Reasoning
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• OpenVLA: An Open-Source Vision-Language-Action Model
• Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success
• RoboMamba: Efficient Vision-Language-Action Model for Robotic Reasoning and Manipulation
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation
• Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning
• Action-aware Dynamic Pruning for Efficient Vision-Language-Action Manipulation
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• GeoVLA: Empowering 3D Representations in Vision-Language-Action Models
• Octo: An Open-Source Generalist Robot Policy
• VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching
• EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models
• DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
• SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference
• TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving