Tony Wu
@tonywu_71
Multimodal, RAG, Agents | ColPali co-first author | @centralesupelec ๐ซ๐ท x @Cambridge_Uni ๐ฌ๐ง | Core Researcher at @hcompany_ai ๐ง๐ปโ๐ป
545 Following 1.5K Followers
๐ Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual efficient Encoders
One bidirectional Transformer processes text tokens and raw image patches, with no pretrained vision tower, text encoder, or decoder. (1/N ๐งต)
Show more
And STv6 supports ColPali-like models out-of-the-box, with beloved features like token pooling and similarity maps for interpretability!
