Get the latest tech news

Tiny-diffusion: A minimal implementation of probabilistic diffusion models


A minimal PyTorch implementation of probabilistic diffusion models for 2D datasets. - tanelp/tiny-diffusion

The current model configuration doesn't work well on the line dataset, which I consider the most basic among them. The capacity of the model doesn't seem to be a bottleneck, as similar results are obtained across various hidden layer sizes. The use of sinusoidal embeddings for the inputs helps with learning high-frequency functions in low-dimensional problem domains, such as mapping each (x, y) pixel coordinate to (r, g, b) color, as demonstrated in this study.

Get the Android app

Or read this on Hacker News

Read more on:

Photo of Diffusion

Diffusion

Related news:

News photo

Diffusion vs. Autoregressive Language Models: A Text Embedding Perspective

News photo

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

News photo

Beyond Diffusion: Inductive Moment Matching