PolyGemma
Software / AppMentioned in 1 video
A model that uses a decoder-only Transformer and location tokens for pixel space understanding, with PolyGemma 2 showing improved capacity.
A model that uses a decoder-only Transformer and location tokens for pixel space understanding, with PolyGemma 2 showing improved capacity.
![Best of 2024 in Vision [LS Live @ NeurIPS]](https://i.ytimg.com/vi/76EL7YVAwVo/maxresdefault.jpg)