dense-retrieval

Tag

Cards List
#dense-retrieval

@raphaelsrty: We're releasing LateOn and DenseOn today. Two open retrieval models, 149M parameters each. LateOn (ColBERT, multi-vecto…

X AI KOLs Following ↗ · 2026-04-21 Cached

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.

0 favorites 0 likes
#dense-retrieval

Spectral Tempering for Embedding Compression in Dense Passage Retrieval

arXiv cs.CL ↗ · 2026-04-20 Cached

Spectral Tempering (SpecTemp) proposes a learning-free method for embedding compression in dense passage retrieval that adaptively determines optimal spectral scaling based on signal-to-noise ratio analysis, outperforming fixed hyperparameter approaches like PCA and whitening.

0 favorites 0 likes
#dense-retrieval

@lateinteraction: The keynote recording is now on YouTube, for everyone who asked us to host it outside X. https://youtube.com/watch?v=Z2…

X AI KOLs Timeline ↗ · 2026-04-13 Cached

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.

0 favorites 0 likes
← Previous
← Back to home

Submit Feedback