Google's DiffusionGemma proves you don't need to train from scratch to build a text diffusion model

资讯摘要

Google's DiffusionGemma proves you don't need to train from scratch to build a text diffusion model Instead of training a new model from scratch, Google DeepMind retrofitted Gemma 4 into a diffusion model. The newly published report explains how it works and where the tradeoffs are. Google DeepMind released DiffusionGemma as a model in mid-June and has now followed up with the technical report. Unlike standard language models that generate text one token at a time, DiffusionGemma refines blocks of 256 tokens in parallel, similar to how image AIs pull a picture out of noise.

来源与参考

1. 原始链接
2. Google's DiffusionGemma proves you don't need to train from scratch to build a text diffusion model