How this analysis was created: This summary and feature list were written by an AI model that read the project's README and public documentation pages. Each feature links to the documentation it came from; stars, license and language come straight from the GitHub API. The model does not read the source code, and the analysis is refreshed when the project is re-analysed. Learn more on our About page.
This is the official implementation of the paper: A Cheaper and Better Diffusion Language Model with Soft-Masked Noise.
Continuous Latent Diffusion Language Model — a hierarchical latent-space text diffusion model with a block-causal DiT prior over a Text VAE.
We introduce Text-to-text Self-conditioned Simplex Diffusion (TESS), a text diffusion model that is fully non-autoregressive, employs a new form of self-conditioning, and applies the diffusion process on the logit simplex space rather than the typical learned embedding space.
Yun-Yen Chuang · Hung-Min Hsu · Kevin Lin · Chen-Sheng Gu · Ling-Zhen Li · Ray-I Chang · Hung-yi Lee [Slide] [Poster]
The main features of meta-diffub/meta-diffub are: Continuous Diffusion Models.
Open-source alternatives to meta-diffub/meta-diffub include: amazon-science/masked-diffusion-lm — This is the official implementation of the paper: A Cheaper and Better Diffusion Language Model with Soft-Masked Noise. ashaba1in/smoothie — Paper: https://arxiv.org/pdf/2505.18853. bytedance-seed/cola-dlm — Continuous Latent Diffusion Language Model — a hierarchical latent-space text diffusion model with a block-causal DiT… david3684/flm — Flow Map Language Models: One-step Language Modeling via Continuous Denoising. guangyliu/latentops — Source code of paper: Composable Text Controls in Latent Space with ODEs. allenai/tess-diffusion — We introduce Text-to-text Self-conditioned Simplex Diffusion (TESS), a text diffusion model that is fully…
