AI News HubLIVE
原文2 min read

Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

Language-Instructed Vision Embeddings (LIVE) uses language as high-level guidance to produce task-centric embeddings at inference time, removing the need for task-specific retraining. It reduces visual hallucinations by 34 points on MMVP, surpasses much larger vision-language models on VQA, and generalizes to unseen instructions and tasks.

SourcearXiv Computer VisionAuthor: Chengzhi Mao, Xudong Lin, Wen-Sheng Chu

[2606.19584] Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

[Submitted on 17 Jun 2026]

Title:Language-Instructed Vision Embeddings for Controllable and Generalizable Perception

View a PDF of the paper titled Language-Instructed Vision Embeddings for Controllable and Generalizable Perception, by Chengzhi Mao and 2 other authors

View PDF HTML (experimental)

Abstract:Vision foundation models are typically trained as static feature extractors, placing the burden of task adaptation onto large downstream models. We propose an alternative paradigm: instead of solely feeding visual features into language models, we use language itself to dynamically guide the vision encoder. Our method, Language-Instructed Vision Embeddings (LIVE), leverages language as high-level guidance to produce task-centric embeddings at inference time, removing the need for task-specific retraining. This enables the encoder to focus on contextually relevant aspects of the input, yielding more controllable and generalizable representations. Empirically, LIVE reduces visual hallucinations (+34 points on MMVP), surpasses vision-language models with orders of magnitude more parameters on visual question answering, and generalizes to unseen instructions and tasks -- offering a direct path toward adaptive, instruction-driven visual intelligence.

Subjects:

Computer Vision and Pattern Recognition (cs.CV)

Cite as: arXiv:2606.19584 [cs.CV]

(or arXiv:2606.19584v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2606.19584

arXiv-issued DOI via DataCite (pending registration)

Journal reference: Published as a conference paper at ICLR 2026

Submission history

From: Chengzhi Mao [view email] [v1] Wed, 17 Jun 2026 20:39:04 UTC (18,421 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Language-Instructed Vision Embeddings for Controllable and Generalizable Perception, by Chengzhi Mao and 2 other authors

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?)