Sign inSign in

Lucas Beyer

Co-Creator of Vision Transformer · Stanford University · Distinguished

Lucas Beyer is a computer vision and deep learning researcher at Google Brain and OpenAI who co-created the Vision Transformer (ViT) and SigLIP.

More

Lucas Beyer is a computer vision and deep learning researcher at Google Brain and OpenAI who co-created the Vision Transformer (ViT) and SigLIP. His Stanford CS25 lecture covers the VTAB benchmark, scaled supervised pre-training and ViT's patch embeddings, and assumes deep learning.

lectures
6
series
1
hours
6

Start here

Series and courses

In these lectures

Draws on

People cited in the lectures, at the moment of the citation.

  • Catherine OlssonAnthropic colleague cited on the title slide.15:15
  • Nelson ElhageAnthropic colleague cited on the title slide.15:15
  • Chris OlahLecturer and Anthropic colleague cited on the title slide.15:15
  • Lukasz KaiserGoogle researcher cited as a colleague during Aidan Gomez's internship.7:21
  • Noam ShazeerGoogle researcher mentioned as working on autoregressive models.7:28
  • Jakob UszkoreitGoogle researcher mentioned as part of the transformer project.7:48

Playlists

1

About

Lucas Beyer is a computer vision and deep learning researcher at Google Brain and OpenAI who co-created the Vision Transformer (ViT) and SigLIP. His Stanford CS25 lecture covers the VTAB benchmark, scaled supervised pre-training and ViT's patch embeddings, and assumes deep learning.

Connections

13

Their places, courses, books and lectures.