Aurélien Lac(@Aurelien_L_):⚡ A lot of representation models still start from a massive generative VLM. We trained an encoder from scratch instead: native on text and images, multilingual, and built to be fast from the beginning. I’m super proud to share NeoMME with my friend @tonywu_71. 260M and 800M, no vision tower. We also fine-tuned a visual document retriever on top: NeoMME-Retriever.

2026.09.03 13:16

⚡ A lot of representation models still start from a massive generative VLM. We trained an encoder from scratch instead: native on text and images, multilingual, and built to be fast from the beginning. I’m super proud to share NeoMME with my friend @tonywu_71. 260M and 800M, no vision tower. We also fine-tuned a visual document retriever on top: NeoMME-Retriever.