Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
This paper investigates weight pruning for Vision-Language Models (VLMs) in egocentric visual understanding to achieve low-latency inference while preserving doubly-correct predictions—both accurate and evidence-grounded. Existing pruning methods often maintain evidence localization but degrade accuracy. The authors propose a rationale-informed pruning strategy that aligns evidence with decisions, achieving state-of-the-art accuracy and doubly-correct predictions on egocentric video benchmarks.
[2606.25160] Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
[Submitted on 23 Jun 2026]
Title:Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding
View a PDF of the paper titled Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding, by Qitong Wang and 4 other authors
View PDF HTML (experimental)
Abstract:The rapid rise of Vision-Language Models (VLMs) in egocentric visual understanding has made low-latency inference in human-robot collaborative (HRC) tasks increasingly critical. Weight pruning techniques developed for VLMs to shrink model size and computation can be readily applied to satisfy the efficiency demands of on-board processing and real-time interactive robotics. Moreover, safe human-robot interaction demands pruning strategies that preserve doubly-correct predictions; outputs must be both accurate and evidentially grounded to mitigate risks and ensure user trust. In this paper, we present a new study of VLM pruning through the lens of doubly-correct prediction. Our experiments surprisingly show that existing pruning methods often preserve the right evidence localization but undermine correct prediction. To address this, we propose a rationale-informed pruning strategy that better aligns evidence with decisions. Benchmark results on egocentric video datasets demonstrate that our method not only achieves the highest prediction accuracy but also outperforms existing approaches in attaining doubly-correct predictions. We aim to stimulate research on efficient and reliable VLMs, ensuring accuracy-driven advances align with the transparency, auditability, and safety required for responsible human-robot interaction and embodied intelligence.
Comments: International Conference on Intelligent Robots and Systems (IROS) 2026
Subjects:
Robotics (cs.RO); Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2606.25160 [cs.RO]
(or arXiv:2606.25160v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.25160
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Qitong Wang [view email] [v1] Tue, 23 Jun 2026 20:46:54 UTC (1,322 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Toward Low-Latency Vision-Language Models with Doubly-Correct Predictions in Egocentric Visual Understanding, by Qitong Wang and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.RO
new | recent | 2026-06
Change to browse by:
cs cs.CV
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?)