Learning notes on diffusion language models: from the masked-diffusion objective to sampling, scaling, and fast inference.https://buffett0323.github.io/https://buffett0323.github.io/blog/posts/why-diffusion/https://buffett0323.github.io/blog/posts/why-diffusion/The case for diffusion language models: generating text by filling in blanks, many at once, instead of one token per forward pass.Sat, 26 Sep 2026 00:00:00 GMT