PaliGemma 2: A Family of Versatile VLMs for Transfer

Researcher 8 reports

Jiahui Yu

Google Gemini

Jiahui Yu is a Research Lead at OpenAI leading the Perception team. His homepage notes prior co-leadership on Gemini Multimodal at Google DeepMind and work on deep learning and high-performance computing.

Researcher 2 reports

Lucas Beyer

Google Gemini

Lucas Beyer is an ML researcher at Google DeepMind in Zurich. His public homepage highlights prior work at Google Brain and a PhD at ETH Zurich.

Researcher 2 reports

Xiaohua Zhai

Google Gemini

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

Researcher 1 reports

Antonio Torralba

Google Gemini

Antonio Torralba is the Delta Electronics Professor in the EECS Department at MIT and a member of CSAIL whose research focuses on computer vision, visual learning, and scene understanding.

Researcher 1 reports

Mikhail Ryabinin

Google Gemini

Mikhail Ryabinin is listed as an author of the Google technical report PaliGemma 2: A Family of Versatile VLMs for Transfer.

Researcher 1 reports

Matias Mazzocconi

Google Gemini

Matias Mazzocconi is listed as an author of the Google technical report PaliGemma 2: A Family of Versatile VLMs for Transfer.

Researcher 1 reports

Andrew Shen

Google Gemini

Andrew Shen is listed as an author of the Google technical report PaliGemma 2: A Family of Versatile VLMs for Transfer.

Researcher 1 reports

Bilal Mustafa

Google Gemini

Senior research scientist at Google DeepMind.

Researcher 1 reports

Alexander Kolesnikov

Google Gemini

Alexander Kolesnikov is a Research Scientist at Google DeepMind exploring multimodal general intelligence.

Researcher 1 reports

Olivier Henaff

Google Gemini

Research scientist at Google DeepMind working on deep learning, reinforcement learning, self-supervised learning, and robotics.

Researcher 1 reports

Andrea Steiner

Google Gemini

Research scientist at Google DeepMind working on multimodal generative models, visual generation, and image editing; previously completed a PhD at TU Munich.

Researcher 1 reports

Rohit Saxena

Google Gemini

Rohit Saxena is a Research Scientist at Google DeepMind working on visual perception, multimodal learning, and language understanding.

Researcher 1 reports

Andrea Dafoe

Google Gemini

Andrea Dafoe is a senior research scientist at Google DeepMind whose work focuses on frontier AI risks, international governance, and the societal impacts of advanced AI.