# SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models

- Source: arXiv cs.RO
- Published: 2026-11-02T05:00:00.000Z
- RoboHot: https://robohot.news/en/items/nv8nn2vsk5djwi1e1qm5tdon4
- Original: https://arxiv.org/abs/2610.41408

## Summary

SACQ is an ultra-low-bit weight quantization framework for Vision-Language-Action (VLA) models, combining structure-aware codebook fitting, action-aware mixed-bit allocation, and two-stage post-quantization refinement.