← Back to all news
arXiv Machine Learning By Haesung Lee, Insu Han

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

Read the original on arXiv Machine Learning →

SACQ is a weight‑only vector‑codebook quantization framework designed for Vision‑Language‑Action models, addressing the challenges of ultra‑low‑bit precision. It incorporates structure‑aware codebook fitting, action‑aware mixed‑bit allocation, and a two‑stage post‑quantization refinement to maintain policy performance. Experiments on GR00T N1.7 and SimplER show that SACQ achieves high success rates (up to 93.85%) while reducing memory usage by 4.83× and improving inference speed.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 21

HBVLA: Pushing 1-Bit Post-Training Quantization for Vision-Language-Action Models

arXiv:2602. 13710v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models enable instruction-following embodied control, but their large compute and memory footprints hinder deployment on resource-constrained robots and edge platforms.

By Xin Yan, Zhenglin Wan, Feiyang Ye, Xingrui Yu, Hangyu Du, Yang You, Ivor Tsang
roboticsefficiencymultimodalbenchmarks
More like this →
arXiv AI
Jun 8

ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

arXiv:2605. 24011v2 Announce Type: replace-cross Abstract: Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical.

By Arash Akbari, Arman Akbari, Masih Eskandar, Qitao Tan, Yixiao Chen, Jingwu Luo, Bertha Pangaribuan, Liyun Zhang, Jennifer Dy, Geng Yuan, Xue Lin, Gaowen Liu, Stratis Ioannidis, Yanzhi Wang
agentsroboticsefficiencymultimodalbenchmarks
More like this →
arXiv AI
21h ago

ActQuant: Sub-4-bit Action-Guided Backbone Weight-Only Quantization for Vision-Language-Action Models

ActQuant is a mixed‑precision post‑training quantization framework that reduces Vision‑Language‑Action model weights to sub‑4‑bit precision. It first allocates a single bit‑width to each weight matrix based on its contribution to action prediction, then optimizes per‑block scales using action‑aware curvature to focus dynamic range on control‑critical weights. Coupled with the OmniModel.cpp conversion pipeline, ActQuant enables deployment on edge devices, achieving up to 2.5 bits‑per‑weight while preserving over 90 % of baseline performance on both simulation and a real 6‑DoF UR3 robotic arm.

By Arash Akbari, Arman Akbari, Masih Eskandar, Qitao Tan, Yixiao Chen, Jingwu Luo, Bertha Pangaribuan, Liyun Zhang, Jennifer Dy, Geng Yuan, Xue Lin, Gaowen Liu, Stratis Ioannidis, Yanzhi Wang
agentsroboticsefficiencymultimodalbenchmarks
More like this →