TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Arctic Embed 2.0 interview with Authors

2 pointsby CShorten5 months ago
The Arctic Embedding model series from Snowflake has been one of the most impactful open-source text embedding models! In addition to the open model, which has helped a lot of companies kick off their own inference and fine-tuning services (including us at Weaviate), the Snowflake team has also published incredible research breaking down all the components of how to train these models!<p>I am SUPER EXCITED to share the 110th Weaviate Podcast interviewing Arctic Embed co-authors Luke Merrick and Puxuan Yu -- further joined by Charles Pierse from Weaviate, discussing all things Arctic Embed!<p>The podcast covers the origin of Arctic Embed, pre-training embedding models, Matryoshka Representation Learning, fine-tuning embedding models, synthetic query generation, hard negative mining, and lastly a topic I personally find very interesting: Perspectives on single-vector embedding models compared to ColBERT, SPLADE, or Re-rankers.<p>I hope you enjoy the podcast!<p>YouTube: https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=Kjqv4uk3RCs<p>Spotify: https:&#x2F;&#x2F;creators.spotify.com&#x2F;pod&#x2F;show&#x2F;weaviate&#x2F;episodes&#x2F;Arctic-Embed-with-Luke-Merrick--Puxuan-Yu--and-Charles-Pierse---Weaviate-Podcast-110-e2sg168&#x2F;a-abmi4qd

no comments

no comments