@raphaelsrty: We're releasing LateOn and DenseOn today. Two open retrieval models, 149M parameters each. LateOn (ColBERT, multi-vecto…
Summary
Raphael released two open-source retrieval models, LateOn (ColBERT multi-vector) and DenseOn (single-vector), each 149M parameters and outperforming 4× larger models on BEIR.
View Cached Full Text
Cached at: 04/21/26, 05:13 PM
We’re releasing LateOn and DenseOn today. Two open retrieval models, 149M parameters each. LateOn (ColBERT, multi-vector): 57.22 NDCG@10 on BEIR. DenseOn (dense, single-vector): 56.20. Both beat models up to 4× larger We’re open-sourcing the weights under Apache 2.0
Similar Articles
@antoine_chaffin: The new generation of open state-of-the-art single and multi-vector retrieval models is here It's time, DenseOn with th…
LightOn releases DenseOn and LateOn, a new generation of open state-of-the-art single and multi-vector retrieval models that outperform existing ones.
@raphaelsrty: At 140 million parameters, our LateOn model yield strong results Unrelated to LateOn, I'm really excited by what's happ…
The LateOn model with 140M parameters achieves strong results, and the community is excited about advances in multi-vector models including new CPU indexes and multilingual support.
DenseOn with the LateOn: Fully Open Dense and Late-Interaction Models for Multilingual, Long-Context, and Code Search
This paper presents fully open DenseOn and LateOn retrieval models, trained on curated English data and extended to multilingual settings via translate-train, achieving state-of-the-art BEIR results for their parameter size.
@antoine_chaffin: It’s only BEIR but there are almost 10 points gap between v2 and LateOn We also have good evidence that the model gener…
LateOn, a new generation ColBERT model, achieves a nearly 10-point improvement over v2 on BEIR and generalizes well outside BEIR, with the same usage in PyLate.
@liquidai: Introducing LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M: two multilingual retrieval models built for ultra-fast and a…
Liquid AI introduces LFM2.5-Embedding-350M and LFM2.5-ColBERT-350M, two multilingual retrieval models optimized for fast and accurate search across 11 languages, with latency as low as 1.5ms.