🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Excited to see Andrew Yates also talking about DeepImpact

Glad to see our work on improved LSR with corpus specific vocabulary mentioned by Andrew Yates

Excited to see Sean MacAvaney adding Pinecone's reranker and sparse model to Terrier! Such a powerful integration for IR research and applications. 🚀 github.com/seanmacavaney/…

Congratulations to our very own Antonio Mallia, Cesare Campagnano, and @JackPertschuk – as well as their co-authors – on their accepted #ECIR2025 research papers! 🎉 They continue to push the state-of-the-art forward on information retrieval, and we as an industry are better for it!

We are very excited to share that the work of Cesare Campagnano , Antonio Mallia , @JackPertschuk and Fabrizio Silvestri has been accepted to #ECIR2025 as a #shortpaper. See you in #Lucca. ECIR2025 Pinecone #AI #Research #IR #industry

A bunch of people asked me what a "sparse" vector is, so I wrote an explanation (and Pinecone now supports them!) pinecone.io/learn/sparse-r…

Just read Arjun Patel's latest article on Pinecone’s brand-new sparse index and model capabilities—highly recommend it if you’re curious about how keyword search and sparse models fit into the bigger picture of vector search. pinecone.io/learn/learn-pi…

Super team of strong IR experts! Glad to see such a massive push coming from Glasgow IR Group I am personally looking forward to meeting the whole team at ECIR2025

It was a really pleasant surprise to learn that our paper “Efficient Constant-Space Multi-Vector Retrieval” aka ConstBERT, co-authored with Sean MacAvaney and Nicola Tonellotto received the Best Short Paper Honourable Mention at ECIR 2025! #ECIR2025 #IR #Pinecone

If you are attending ECIR, do not miss our talk at the Industry Day: "Neural Retrieval Meets Cascading Architectures" with Cesare Campagnano and Jack Pertschuk showcasing how to perform SOTA retrieval with a few lines of code using Pinecone. Thursday @ 16:30 in Guinigi Chapel – IMT

Want to build LLM-quality search without an LLM latency hit? We just open-sourced constBERT, a novel late-interaction model that boosts NDCG by up to 27% with only a few extra millis of latency on your existing Pinecone index. Technical blog: pinecone.io/blog/cascading…

Refreshing BERT – a groundbreaking shift in NLP BERT, or Bidirectional Encoder Representations from Transformers, was the first to pre-train a deep Transformer in a bidirectional way: ▪️It processes both left and right context of a word at the same time, to deeper understand

Thanks so much! 🙏 It's always a pleasure to share what we're working on at @Pinecone. BERT continues to be a solid foundation for retrieval research, and with ConstBERT, we're excited to push the boundaries of what’s possible in multi-vector search. Appreciate the shoutout!

youtu.be/t_ALyJ174gs?si… Recording of my talk from RustWeek out now - blog post coming soon! It was a blast to meet so many folks who share a love of writing high performance Rust. Huge thanks to the RustNL team for a phenomenal conference - in a movie theatre of all places!