@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…
Summary
LightOn releases DenseOn and LateOn, a new generation of open state-of-the-art single and multi-vector retrieval models that outperform existing ones.
View Cached Full Text
Cached at: 04/22/26, 04:13 AM
The new generation of open state-of-the-art single and multi-vector retrieval models is here It’s time, DenseOn with the LateOn @LightOnIO releases models that leap past existing ones, and everything you need to do the same!
Similar Articles
@raphaelsrty: We're releasing LateOn and DenseOn today. Two open retrieval models, 149M parameters each. LateOn (ColBERT, multi-vecto…
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.
@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.
@SilvioMartinico: The late-interaction multivector retrieval ecosystem is exploding right now. To help separate the signal from the noise…
A curated list of top models, engines, libraries, and datasets for late-interaction multivector retrieval, organized in an 'Awesome Multivector Retrieval' resource.
@LightOnIO: 50 million downloads on @huggingface! LightOn SOTA late-interaction and dense retrievers, OCR models, and LLMs are vali…
LightOn celebrates 50 million downloads on Hugging Face for its state-of-the-art retrieval, OCR, and language models, validated by the community and in production.
@lateinteraction: Late-interaction sparse retrieval? With neuron-level inverted indexing, on top of unsupervised sparse autoencoders. Wor…
This paper presents a single-stage sparse coding method using unsupervised sparse autoencoders and natural inverted indexing to accelerate multi-vector retrieval, outperforming traditional k-means based approaches.