notesum.ai

Published at November 21

Multimodal Autoregressive Pre-training of Large Vision Encoders

cs.CV

Released Date: November 21, 2024

Authors: Enrico Fini¹, Mustafa Shukor¹, Xiujun Li¹, Philipp Dufter¹, Michal Klein¹, David Haldimann¹, Sai Aitharaju¹, Victor Guilherme Turrisi da Costa, Louis Béthune, Zhe Gan¹, Alexander T Toshev, Marcin Eichner¹, Moin Nabi¹, Yinfei Yang¹, Joshua M. Susskind, Alaaeldin El-Nouby¹

Aff.: ¹Apple

Arxiv: http://arxiv.org/abs/2411.14402v1