Diffusion models from scratch, from a new theoretical perspective(chenyang.co)

342 points by jxmorris12 2 years ago | 36 comments

A tutorial blog post by Chenyang Yuan explaining diffusion models from scratch through a new theoretical perspective.

Andrew Ng on DeepSeek(deeplearning.ai)

21 points by amrrs 1 year ago | 2 comments

How to build a diffusion language model(kuleshov-group.github.io)

162 points by volodia 1 month ago | 19 comments

Learning the Integral of a Diffusion Model(sander.ai)

142 points by benanne 5 months ago | 21 comments

Diffusion Forcing: Next-Token Prediction Meets Full-Sequence Diffusion(boyuan.space)

200 points by magoghm 2 years ago | 12 comments

Can LLMs learn from a single example?(fast.ai)

387 points by jdkee 3 years ago | 117 comments

A fast.ai blog post by Jeremy Howard and Jonathan Whitaker on unusual fine-tuning loss curves suggesting LLMs can memorize examples after seeing them once.