5:01

Convolutional Differentiable Logic Gate Networks - NeurIPS Oral - difflogic

15:43

Vision Transformers - The big picture of how and why it works so well.

8:39

Why Computer Vision Is a Hard Problem for AI

5:13

Newton Losses: Using Curvature Information for Learning with Differentiable Algorithms - NeurIPS2024

8:48

Large Language Models explained briefly

12:16

How to combine classic algorithms and AI - Learning with Algorithmic Supervision via Relaxations

1:31:13

A Hackers' Guide to Language Models

8:25

Monotonic Differentiable Sorting Networks for Learning to Rank (diffsort)