Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
Mix-QVLA is a task-evidence-aware mixed-precision post-training quantization framework for VLA models. It evaluates whether quantization preserves task-relevant evidence and dynamically adjusts layer precision, achieving high accuracy with significant memory reduction and speedup. On LIBERO, it reduces memory from 15.4 GB to 4.1 GB, retains 96.3% success rate, and achieves 1.52x inference speedup.
[2606.19565] Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
[Submitted on 17 Jun 2026]
Title:Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models
View a PDF of the paper titled Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models, by Navin Ranjan and Andreas Savakis
View PDF HTML (experimental)
Abstract:We propose Mix-QVLA, a task-evidence-aware mixed-precision PTQ framework for VLA models. Mix-QVLA anchors each quantized variant to the full-precision action-token reference decision and evaluates whether quantization preserves task-relevant evidence across key VLA functional boundaries. It computes normalized gradient-weighted task-evidence maps from boundary activations and compares full-precision and quantized maps using evidence-mass and attribution-distribution distortion, capturing changes in both the strength and allocation of decision-supporting evidence. A soft-bottleneck objective aggregates boundary-level degradation into layer-wise sensitivity scores. Mix-QVLA further models sensitivity throughout task execution, capturing phase-dependent shifts in layer importance rather than assuming a fixed sensitivity profile. The resulting evidence- and time-aware scores guide mixed-precision bit allocation under model-size and BitOps budgets. Extensive evaluations on OpenVLA-style policies show that Mix-QVLA improves the accuracy-efficiency trade-off of low-bit VLA deployment. On LIBERO, Mix-QVLA reduces OpenVLA-OFT memory from 15.4 GB to 4.1 GB, retains 96.3 average success compared with 97.1 for the BF16 model, and achieves a 1.52x inference speedup.
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2606.19565 [cs.CV]
(or arXiv:2606.19565v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2606.19565
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Navin Ranjan [view email] [v1] Wed, 17 Jun 2026 20:08:14 UTC (1,378 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Mix-QVLA: Task-Evidence-Aware Mixed-Precision Quantization of Vision-Language-Action Models, by Navin Ranjan and Andreas Savakis
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-06
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
Loading...
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
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)