Metraipolis › archive › dc_2a8dbbfbeff6

SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models — arXiv:2610.41408

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.41408
License (as archived): CC0-1.0
Archived: 2026-11-02T04:53:14.119Z
SHA-256 of the archived text: 6cbd4e67b5cefc6eec6d4438f7fa35e437ceaec15a38f82290bd24e5b9015e33
Stable URL of this page: https://metraipolis.com/documento/dc_2a8dbbfbeff6

How to cite

SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models — arXiv:2610.41408 — arXiv (en), https://arxiv.org/abs/2610.41408 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a8dbbfbeff6 (Metraipolis archive dc_2a8dbbfbeff6, sha256 6cbd4e67b5cefc6eec6d4438f7fa35e437ceaec15a38f82290bd24e5b9015e33)

BibTeX

@misc{dc2a8dbbfbeff6,
  title = {SACQ: Structure-Aware Codebook Quantization for Ultra-Low-Bit Vision-Language-Action Models — arXiv:2610.41408},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.41408},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a8dbbfbeff6; sha256 6cbd4e67b5cefc6eec6d4438f7fa35e437ceaec15a38f82290bd24e5b9015e33},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41408. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-Language-Action (VLA) models enable capable robot behavior, but their large memory footprint limits deployment on resource-constrained robotic platforms. Weight quantization is a natural remedy, yet post-training quantization (PTQ) recipes inherited from large language models degrade when applied to VLAs at ultra-low precision. Existing low-bit PTQ methods often fail to explicitly account for the structure of downstream operations and allocate precision without considering its effect on the policy actions. We introduce SACQ, an ultra- low-bit weight-only vector-codebook quantization framework for VLAs. SACQ combines (1) structure-aware codebook fitting with role-specific quadratic metrics that reflect input statistics and downstream sensitivity; (2) action-aware mixed-bit allocation based on the increase in final-action error as individual layers are compressed; and (3) two-stage post-quantization refinement that reassigns codeword indices with second-order error compensation and calibrates codebooks and row-group scales against the decoded action. Using GR00T N1.7, SACQ achieves 93.85% average success across four LIBERO suites at 1.5 bits per language/action weight while reducing model memory by 4.83x. With INT8 activation quantization and low-precision attention, it retains 93.55% success while running 1.51x faster than BF16. On SimplER, SACQ further achieves 63.76% and 52.27% success under Visual Matching and Variant Aggregation at 2 bits per language/action weight, compared to 58.90% and 53.45% for BF16, respectively.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG); Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.41408 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-02T04:45:12.955Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).