Hcompany/NeoMME-800M-Retriever-ST-late Visual Document Retrieval • 0.8B • Updated 6 days ago • 38 • 4
Hcompany/NeoMME-260M-Retriever-ST-late Visual Document Retrieval • 0.3B • Updated 6 days ago • 89 • 5
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference Paper • 2609.01657 • Published 9 days ago • 27
NeoMME Collection Meet NeoMME: a family of 260M and 800M Multimodal-Native Multilingual Encoders • 12 items • Updated 6 days ago • 30
view article Article Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers tomaarsen • 14 days ago • 123
view reply Nice work! Thank you very much for the evals. Just wild to see our 300M model to be this strong against much larger dense systems.
view article Article mLateOn: A New SoTA for Multilingual ColBERT-Style Retrieval, Evaluated on HAKARI-Bench hotchpotch • 27 days ago • 8