PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action Models

arXiv:2610.25961 · cs.RO, cs.AI · Submitted 2026-10-19 · Read on arXiv

cs.RO, cs.AI

Submitted: 2026-10-19

Updated: 2026-10-19

Comments: 25 pages, 7 figures, 10 tables. Project page: https://pacevla.github.io/

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

Terminology

• Quantization — 1× in this paper · explained in 14 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
• 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