@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.
@lateinteraction: The keynote recording is now on YouTube, for everyone who asked us to host it outside X. https://youtube.com/watch?v=Z2…
A keynote recording argues that late interaction retrieval (e.g., ColBERT-style) is the most promising direction in AI-scale information retrieval research, contending that single-vector dense retrieval is fundamentally flawed and that the IR community must raise its ambitions significantly. The talk introduces the LIMIT benchmark as evidence of dense retrieval's generalization failures and calls for a paradigm shift by 2030.
@eliebakouch: very nice release by @OpenAI! a 50M active, 1.5B total gpt-oss arch MoE, to filter private information from trillion sc…
OpenAI released a 1.5B-parameter MoE model with only 50M active parameters that can filter private data from trillion-token datasets while maintaining 128k context length.
New embedding models and API updates
OpenAI released two new embedding models: text-embedding-3-small (5x cheaper than ada-002 with 40%+ MIRACL improvement) and text-embedding-3-large (best performance with up to 3072 dimensions). Both models show significant performance gains on standard benchmarks while reducing costs.
@Julian_a42f9a: Late-interaction retrieval models are widely used for their strong performance, but their representations can be utiliz…
A new paper shows that late-interaction retrieval model representations can effectively replace raw document text in RAG tasks, extending their utility beyond retrieval.