AI News HubLIVE
原文2 min read

How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A

Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling question: as multimodal models grow, how many visual tokens are actually needed, and how should they be allocated under a fixed visual token budget? Existing training-free pruning methods typically answer this with one-shot proxies such as decoder attention, visual similarity, or conditional diversity. We argue that visual token pruning is better viewed as task-conditioned evidence search, especially under aggressive compression and across model scales. We propose F^3A, a training-free router for visual token pruning that operates before the language model consumes image tokens. F^3A builds lightweight question-conditioned cues, matches them to visual-grid tokens through frozen sparse sensing heads, and allocates a fixed vision token budget via coarse evidence localization, local refinement, coverage-preserving competition, and recovery of under-covered regions. It requires no model training, no extra LLM forward pass and preserves the original multimodal prompting and decoding pipeline.

SourcearXiv Computer VisionAuthor: YiJie Huang, Yiqun Zhang, Zhuoyue Jia, Xiaocui Yang, Junzhao Huang, Zihan Wang, Shi Feng, Daling Wang, Yifei Zhang, Yongkang Liu

[2605.16359] How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A

[Submitted on 9 May 2026]

Title:How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A

View a PDF of the paper titled How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A, by YiJie Huang and 9 other authors

View PDF HTML (experimental)

Abstract:Vision-language models improve perception by feeding increasingly long visual token sequences into language backbones, but the resulting inference cost raises a basic scaling question: as multimodal models grow, how many visual tokens are actually needed, and how should they be allocated under a fixed visual token budget? Existing training-free pruning methods typically answer this with one-shot proxies such as decoder attention, visual similarity, or conditional diversity. We argue that visual token pruning is better viewed as task-conditioned evidence search, especially under aggressive compression and across model scales. We propose F^3A, a training-free router for visual token pruning that operates before the language model consumes image tokens. F^3A builds lightweight question-conditioned cues, matches them to visual-grid tokens through frozen sparse sensing heads, and allocates a fixed vision token budget via coarse evidence localization, local refinement, coverage-preserving competition, and recovery of under-covered regions. It requires no model training, no extra LLM forward pass and preserves the original multimodal prompting and decoding pipeline.

Subjects:

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

Cite as: arXiv:2605.16359 [cs.CV]

(or arXiv:2605.16359v1 [cs.CV] for this version)

https://doi.org/10.48550/arXiv.2605.16359

arXiv-issued DOI via DataCite

Submission history

From: Yijie Huang [view email] [v1] Sat, 9 May 2026 13:13:04 UTC (16,511 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled How Many Visual Tokens Do Multimodal Language Models Need? Scaling Visual Token Pruning with F^3A, by YiJie Huang and 9 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

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?)