2026-05-26原文

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

ActQuant is an action-guided mixed-precision post-training quantization framework for Vision-Language-Action (VLA) models, enabling sub-4-bit weight quantization through a two-stage approach that maintains high success rates on the LIBERO benchmark and a real UR3 robotic arm, significantly reducing memory footprint.

Article intelligence

EngineersAdvanced

Key points

ActQuant employs action-aware mixed-precision quantization to preserve VLA model performance under sub-4-bit weight quantization.
The two-stage framework includes an inter-tensor bit allocator and an intra-tensor scale optimizer focusing on action-critical weights.
Paired with the OmniModel.cpp deployment pipeline, it achieves 2.5 bpw on LIBERO, compressing the backbone by 5.3×.
On a real UR3 arm, quantized π0.5 model retains success rate while reducing memory footprint by 2.5×.

Why it matters

This matters because actQuant employs action-aware mixed-precision quantization to preserve VLA model performance under sub-4-bit weight quantization.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

[2605.24011] ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models

[Submitted on 19 May 2026]

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

View a PDF of the paper titled ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models, by Arash Akbari and 13 other authors

View PDF HTML (experimental)

Abstract:Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressive, sub-4-bit weight quantization is the natural solution, yet existing post-training quantization (PTQ) methods suffer severe performance degradation in this regime. To address this, we introduce ActQuant, an action-guided mixed-precision PTQ framework that operates in two stages: (1) an inter-tensor bit allocator that assigns each weight matrix a single bit-width based on how much it contributes to predicting the agent's actions; (2) an intra-tensor scale optimizer tunes per-block quantization scales using action-aware curvature, so that dynamic range is concentrated on the weights most influential for control. To deliver the on-device benefits of our aggressive quantization, we further introduce this http URL, an agentic conversion pipeline that ports architectures into a native C/C++ runtime with efficient low-bit kernels. We evaluate ActQuant both in simulation and on a real-world 6-DoF UR3 arm, with all models deployed through this http URL. On the LIBERO benchmark, ActQuant is the only method that operates at or below 3 bits-per-weight, retaining 95.0% on OpenVLA-OFT and 94.8% on $\pi_{0.5}$. Pushed further, ActQuant reaches 2.5 bpw at 90.1% on OpenVLA-OFT, compressing the backbone from 14.3 GB to 2.7 GB (5.3$\times$). On the physical UR3 arm, $\pi_{0.5}$ quantized with ActQuant retains the baseline's success rate while reducing the memory footprint by 2.5$\times$.

Subjects:

Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)

Cite as: arXiv:2605.24011 [cs.CV]

(or arXiv:2605.24011v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.24011

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Arash Akbari [view email] [v1] Tue, 19 May 2026 19:57:26 UTC (1,871 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models, by Arash Akbari and 13 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CV

new | recent | 2026-05

Change to browse by:

cs cs.AI

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)