A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. Topics
-
Updated
Mar 27, 2026 - Python
A diffusion-based framework for document OCR that replaces autoregressive decoding with block-level parallel diffusion decoding. Topics
GUI for LLaDA Diffusion LLM with Quantization for low end GPU and CPU options. Now with Prototype Training and Vector DB.
Minimal quickstart fork of the LLaDA repository. Watch text diffusion with a single line of code (& flag).
Implementing Diffusion Models for Language Generation
PyTorch Lightning implementation of LLaDA, a masked-diffusion language model that generates text without autoregression. Includes training, greedy/multinomial sampling, and a generation demo.
Add a description, image, and links to the llada topic page so that developers can more easily learn about it.
To associate your repository with the llada topic, visit your repo's landing page and select "manage topics."