NeoMME
AssessLanguages & Frameworks
A multilingual multimodal encoder family for text and image representation.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by model releases, with 0 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 7Hugging Face Blog·9/3/2026model_releaseNeoMME: an efficient multilingual multimodal encoder
Hugging Face introduced NeoMME, a family of 260M and 800M multimodal encoders built from scratch with a single bidirectional Transformer for text and image patches. The models target visual document retrieval, achieve strong results on ViDoRe v3, and are released in Hugging Face Transformers under Apache 2.0.