Andreas Steiner

6

Papers

254

Total Citations

Papers (6)

On Scaling Up a Multilingual Vision and Language Model

LiT: Zero-Shot Transfer With Locked-Image Text Tuning

MLP-Mixer: An all-MLP Architecture for Vision

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Image Captioners Are Scalable Vision Learners Too