PaliGemma: A versatile 3B VLM for transfer

Research scientist focused on machine learning and natural language understanding, with work spanning machine translation, semantic parsing, and large-scale language modeling.

Jiahui Yu is a research scientist at Google DeepMind working on multimodal learning and large language models.

Chief Technology Officer at Google DeepMind, with work spanning machine learning and reinforcement learning.

Google researcher whose public profile says he joined Google in September 2008 and has been with the Google Brain team since January 2015, with interests spanning information retrieval, learning to rank, machine learning, machine translation, and natural language processing.

Research scientist at Google DeepMind on the Gemini team, working on multimodal AI.

Research scientist at Google DeepMind based in Paris, focused on deep learning and computer vision.

Xiaohua Zhai is a researcher on the Google Research team in Zurich whose work focuses on large multimodal models and efficient deep learning.

Leonardo Beyer is a research scientist at Google DeepMind. His public homepage highlights work across representation learning, multimodal models, and large-scale machine learning systems.

Xiuye Gu is a researcher whose public work focuses on vision-language modeling and machine learning systems.

Maxwell Collins is a Research Scientist at Google DeepMind.

Researcher at Google Research whose public work includes multimodal and vision-language modeling, with arXiv publications tied to PaliGemma and related transfer work.

Staff software engineer at Google DeepMind working on post-training, alignment, multimodal models, and data filtering. He previously worked on hardware and software co-design for machine learning.

Canonical link

Radu Soricut

Jiahui Yu

Koray Kavukcuoglu

Yonghui Wu

Nikolay Savinov

Matthieu Devin

Xiaohua Zhai

Leonardo Beyer

Xiuye Gu

Maxwell Collins

Nan Ding

William Kolesnikov