Faster and Better? Benchmark Bugs and Design Limitations Distort the Evaluation of Vision-Language-Action Acceleration

arXiv:2609.37771 · cs.RO · Submitted 2026-09-29 · Read on arXiv

cs.RO

Submitted: 2026-09-29

Updated: 2026-09-29

Terminology

• Benchmark — 85× in this paper · explained in 2 episodes
• Consistency — 13× in this paper · explained in 3 episodes
• Alignment — 7× in this paper · explained in 1 episode
• In Conference on Robot Learning — 4× in this paper
• Robustness — 3× in this paper · explained in 5 episodes
• Benchmarking — 2× in this paper · explained in 3 episodes
• Conference on Computer Vision and Pattern Recognition — 2× in this paper
• Generalization — 2× in this paper · explained in 13 episodes
• VLA Models — 2× in this paper · explained in 3 episodes
• Action Chunking — 1× in this paper · explained in 1 episode
• CVF International Conference on Computer Vision — 1× in this paper
• Fidelity — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• In International Conference on Machine Learning — 1× in this paper
• Pruning — 1× in this paper · explained in 4 episodes
• Redundancy — 1× in this paper · explained in 2 episodes
• Reinforcement Learning — 1× in this paper · explained in 4 episodes
• Sim-to-Real Transfer — 1× in this paper · explained in 2 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• ProbeFlow: Training-Free Adaptive Flow Matching for Vision-Language-Action Models
• Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Survey
• RLBench: The Robot Learning Benchmark & Learning Environment
• What Are We Actually Benchmarking in Robot Manipulation?
• Evaluating Real-World Robot Manipulation Policies in Simulation
• CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks
• Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAs
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• A New Approach to Time-Optimal Path Parameterization based on Reachability Analysis
• SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
• RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
• Knowing When to Stop: Adaptive Action Chunking via Internal Cross-Attention Dynamics in VLAs
• VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and Robots
• LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization

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