Unified Pix Token And Word Token Generative Language Model
Researchers propose a new generative language model that unifies pix tokens and word tokens to address limitations in visual detail understanding of current Vision Transformers, such as difficulty recognizing small text or numbers in images. The model features per-pix token embedding, color folding, global conditional attention approximation, and unsupervised pretraining. Experiments show good performance even with small models and limited data, and it follows scaling laws.
[2605.14028] Unified Pix Token And Word Token Generative Language Model
[Submitted on 13 May 2026]
Title:Unified Pix Token And Word Token Generative Language Model
View a PDF of the paper titled Unified Pix Token And Word Token Generative Language Model, by Haun Leung and ZiNan Wang
View PDF HTML (experimental)
Abstract:Since the emergence of Vision Transformer (ViT), it has been widely used in generative language model and generative visual model. Especially in the current state-of-art open source multimodal models, ViT obtained by CLIP or SigLIP method serves as the vision encoder backbone to help them acquire visual understanding capabilities. But this method leads to limitations in visual understanding for details, such as difficulty in recognizing small text or numbers in images. To address these issues, we propose a new model to unify pix token and word token into the generative language model. The new model also features with each pix of image having its own token embedding, color folding, global conditional attention approximation and image unsupervised pretraining. We conducted image unsupervised pretraining experiments using our new model to explore its potential. The experimental results show that it has good performance even in small model and with limited training data. We believe our model also conforms to the scaling law, as long as model parameters and training data increased, its performance will continue to improve.
Comments: 13 pages, 6 figures
Subjects:
Computer Vision and Pattern Recognition (cs.CV)
Cite as: arXiv:2605.14028 [cs.CV]
(or arXiv:2605.14028v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2605.14028
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: ZiNAN Wang [view email] [v1] Wed, 13 May 2026 18:38:51 UTC (4,233 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Unified Pix Token And Word Token Generative Language Model, by Haun Leung and ZiNan Wang
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.CV
new | recent | 2026-05
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?)