The papers worth understanding

Train a diffusion model block-by-block, not end-to-end.

The Transformer, from scratch.

The adaptive optimizer that trains almost everything.

Fine-tune giant models by training almost nothing.

Alignment without a reward model.

Sequence modeling without attention.

How noise becomes images.

Why scale changed everything. (GPT-3)

The compute-optimal scaling law.

Teaching images and text to share a space.

A simpler road to generative models.