Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

H Company stories

Sep 6, 2026

H Company releases NeoMME multimodal encoders for visual document retrieval

H Company has launched NeoMME, a family of 260M and 800M parameter single-tower multimodal encoders designed for visual document retrieval. The models represent a departure from existing approaches that repurpose generative vision-language models as encoders.

Sep 6, 2026·1 source
00

H Company releases NeoMME multimodal encoders for visual document retrieval

H Company has launched NeoMME, a family of 260M and 800M parameter single-tower multimodal encoders designed for visual document retrieval. The models represent a departure from existing approaches that repurpose generative vision-language models as encoders.

Sep 6, 2026·1 source
00

Top claims

  • ▪On the BEIR-15 text retrieval benchmark, NeoMME late-interaction scored 0.4881 for the 260M model and 0.5126 for the 800M model, compared to 0.5722 for the 149M-parameter LateOn model.
  • ▪Standard late-interaction indexing for NeoMME yields approximately 1.5 MB per ViDoRe v3 document page in float32 format.
  • ▪A cross-modal ablation probe showed that at 90% masking, visible page patches raised masked-token accuracy by 38.4 points for the NeoMME-260M model and 40.5 points for the NeoMME-800M model.

Topics

Document understandingAI foundation modelsRetrieval-augmented generation (RAG)Multimodal modelsAI research & benchmarks