Genie: Generative Interactive Environments#Machine Learning#Computer Vision#Google#Research#Paper#PDF#Foundation Models#Games#Robotics·arxiv.org·Feb 26, 2024Genie: Generative Interactive Environments
F-VLM: Open-vocabulary object detection upon frozen vision and language models#Computer Vision#Google#Object Detection#Paper·ai.googleblog.com·May 12, 2023F-VLM: Open-vocabulary object detection upon frozen vision and language models
Scaling Vision Transformers to 22 Billion Parameters#Transformers#Computer Vision#Paper#PDF#Google·arxiv.org·Apr 23, 2023Scaling Vision Transformers to 22 Billion Parameters