Books, papers, and people that shape my thinking.

A living collection of the things I find myself coming back to.

Favorite Paper

the one I keep re-reading

CVPR 2022

Masked Autoencoders Are Scalable Vision Learners

Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Dollar, Ross Girshick

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our approach masks random patches of the input image and reconstructs the missing pixels.

CVPR 2022 2022Read on arXiv

Let's get in touch

Drop me a message about anything.

Kostas's Logo

I'm Kostas - a PhD ML Engineer building AI systems that ship to production. Thanks for visiting!

© 2026 Kostas Georgiou