Google's new open model DiffusionGemma generates text from noise instead of word by word
Jonathan Kemper
·
2026-06-11
·
via The Decoder
Google released DiffusionGemma, a 26-billion-parameter model that generates text not token by token but throu…
此内容由惯性聚合(RSS阅读器)自动聚合整理,仅供阅读参考。 原文来自 — 版权归原作者所有。