DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Siyuan, Wang, Tianshi, Li, Fengling, Zhu, Lei, Shen, Heng Tao
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917403424718848
author Xu, Siyuan
Wang, Tianshi
Li, Fengling
Zhu, Lei
Shen, Heng Tao
author_facet Xu, Siyuan
Wang, Tianshi
Li, Fengling
Zhu, Lei
Shen, Heng Tao
contents Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization (PTQ) provides an efficient solution, directly applying PTQ to VLAs often results in severe performance degradation during sequential control. We identify temporal error accumulation as a key factor, where quantization perturbations at the vision-language-to-action interface are progressively amplified, leading to kinematic drift in executed trajectories. To address this issue, we propose Drift-Aware Post-Training Quantization (DA-PTQ), which formulates quantization as a drift-aware optimization problem over sequential decision processes. DA-PTQ consists of two components: (1) Cross-Space Representation Compensation, which mitigates structured distortions between multimodal representations and action space to improve action consistency, and (2) Motion-Driven Mixed-Precision Allocation, which assigns bit-widths by minimizing trajectory-level motion errors. Extensive experiments show that DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings, enabling practical deployment of VLAs on resource-limited robotic platforms.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11572
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
Xu, Siyuan
Wang, Tianshi
Li, Fengling
Zhu, Lei
Shen, Heng Tao
Robotics
Multimedia
Vision-Language-Action models (VLAs) have demonstrated strong potential for embodied AI, yet their deployment on resource-limited robots remains challenging due to high memory and computational demands. While Post-Training Quantization (PTQ) provides an efficient solution, directly applying PTQ to VLAs often results in severe performance degradation during sequential control. We identify temporal error accumulation as a key factor, where quantization perturbations at the vision-language-to-action interface are progressively amplified, leading to kinematic drift in executed trajectories. To address this issue, we propose Drift-Aware Post-Training Quantization (DA-PTQ), which formulates quantization as a drift-aware optimization problem over sequential decision processes. DA-PTQ consists of two components: (1) Cross-Space Representation Compensation, which mitigates structured distortions between multimodal representations and action space to improve action consistency, and (2) Motion-Driven Mixed-Precision Allocation, which assigns bit-widths by minimizing trajectory-level motion errors. Extensive experiments show that DA-PTQ significantly reduces kinematic drift and achieves comparable performance to full-precision models under low-bit settings, enabling practical deployment of VLAs on resource-limited robotic platforms.
title DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action Models
topic Robotics
Multimedia
url https://arxiv.org/abs/2604.11572