VLAQuantBench: Closed-Loop Evaluation of Post-Training Quantization for Vision-Language-Action Models
cs.RO, cs.AI
Submitted: 2026-09-21
Updated: 2026-09-21
Comments: 28 pages, 35 tables, 4 figures
Code: https://github.com/jiuyixu25/VLAQuantBench
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SQAP-VLA: A Synergistic Quantization-Aware Pruning Framework for High-Performance Vision-Language-Action Models
- Quantizing deep convolutional networks for efficient inference: A whitepaper
- SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
- BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation
- HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models
- DyQ-VLA: Temporal-Dynamic-Aware Quantization for Embodied 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
- 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