When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX Variants

arXiv:2609.14146 · cs.RO, cs.LG · Submitted 2026-09-12 · Read on arXiv

cs.RO, cs.LG

Submitted: 2026-09-12

Updated: 2026-09-16

Comments: 6 pages. Code: https://github.com/rafiqul713/smolvla-libero-onnx

Code: https://github.com/rafiqul713/smolvla-libero-onnx

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

Terminology

• Ablation — 1× in this paper · explained in 1 episode
• Quantization — 1× in this paper · explained in 12 episodes

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