RESEARCH PAPERSubmitted 10 Jul 2024

PaliGemma: A versatile 3B VLM for transfer

View all authors

Lucas Beyer; Andreas Steiner; André Susano Pinto; Alexander Kolesnikov; Xiao Wang; Daniel Salz; Maxim Neumann; Ibrahim Alabdulmohsin; Michael Tschannen; Emanuele Bugliarello; Thomas Unterthiner; Daniel Keysers; Skanda Koppula; Fangyu Liu; Adam Grycner; Alexey Gritsenko; Neil Houlsby; Manoj Kumar; Keran Rong; Julian Eisenschlos; Rishabh Kabra; Matthias Bauer; Matko Bošnjak; Xi Chen; Matthias Minderer; Paul Voigtlaender; Ioana Bica; Ivana Balazevic; Joan Puigcerver; Pinelopi Papalampidi; Olivier Henaff; Xi Xiong; Radu Soricut; Jeremiah Harmsen; Xiaohua Zhai

Read on arXiv PDF

Classification

View four quadrants

Major category: Components of WAMs
Quadrant: Not applicable
Architecture: Not applicable
Prediction paradigm: Not applicable
Subcategories: Language & vision-language backbones Language & VLM backbones
Source review status: Verified from primary sources

Category review. PaliGemma is a general visual-language backbone connecting SigLIP image tokens to Gemma with prefix attention and task-adaptation training. The manuscript explicitly names it as a reusable VLM; no robot action or future-state prediction is required for this component role. Reading evidence

AT A GLANCE

Contribution

A contribution summary has not been added yet.

Abstract

An abstract has not been added yet.

Affiliations

Not listed in the collection.

BibTeX

@article{paligemma,
      title={PaliGemma: A versatile 3B VLM for transfer}, 
      author={Lucas Beyer and Andreas Steiner and André Susano Pinto and Alexander Kolesnikov and Xiao Wang and Daniel Salz and Maxim Neumann and Ibrahim Alabdulmohsin and Michael Tschannen and Emanuele Bugliarello and Thomas Unterthiner and Daniel Keysers and Skanda Koppula and Fangyu Liu and Adam Grycner and Alexey Gritsenko and Neil Houlsby and Manoj Kumar and Keran Rong and Julian Eisenschlos and Rishabh Kabra and Matthias Bauer and Matko Bošnjak and Xi Chen and Matthias Minderer and Paul Voigtlaender and Ioana Bica and Ivana Balazevic and Joan Puigcerver and Pinelopi Papalampidi and Olivier Henaff and Xi Xiong and Radu Soricut and Jeremiah Harmsen and Xiaohua Zhai},
      year={2024},
      journal={arXiv:2407.07726},
}

Classification

Contribution

Abstract

Affiliations

BibTeX

More in this category

V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning

DINOv3

World Simulation with Video Foundation Models for Physical AI