Convert your embeddings to spherical coordinates before compression - this trick cuts embedding stor... - 惯性聚合

推荐订阅源

Engineering at Meta

让小产品的独立变现更简单 - ezindie.com

freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More

WordPress大学

宝玉的分享

The Blog of Author Tim Ferriss

Google DeepMind News

CTFtime.org: upcoming CTF events

罗磊的独立博客

SegmentFault 最新的问题

The Register - Security

Hugging Face - Blog

DataBreaches.Net

奇客Solidot–传递最新科技情报

阮一峰的网络日志

Proofpoint News Feed

Visual Studio Blog

aimingoo的专栏

Netflix TechBlog - Medium

酷壳 – CoolShell

Hackread – Cybersecurity News, Data Breaches, AI and More

Y Combinator Blog

博客园 - 【当耐特】

Google Developers Blog

Stack Overflow Blog

Fortinet All Blogs

钛媒体：引领未来商业与生活新知

The Cloudflare Blog

Google Online Security Blog

Hacker News - Newest: "LLM"

博客园 - Franky

Blog — PlanetScale

PCI Perspectives

cs.AI updates on arXiv.org

Jina AI(@JinaAI_)

Multimodal Search✅ Airgapped✅ Apache2✅ v5-omni keeps the v5-text backbone completely frozen and adds pretrained vision and audio encoders c... Today v5-omni is available on Elastic Inference Service, HuggingFace and Jina API. Learn more about ... jina-embeddings-v5-omni is here! Our first universal embedding model for text, images, audio, and vi... Our official CLI for agents https://t.co/XLhRvLRuDc Tweet The trend toward smaller embeddings is a shift. On-device retrieval, browser-based search, and edge ... v5-text uses decoder-only backbones with last-token pooling instead of mean pooling. Four lightweigh... jina-embeddings-v5-text is here! Our fifth generation of jina embeddings, pushing the quality-effic... Text embeddings are widely assumed to be safe, irreversible representations. We show we can reconstr... Check out the live demo https://t.co/W1EXpDFCAL and see it in action. Our read our repo and paper fo... Most don't know (1) how easy it is to invert embedding vectors back into sentences, (2) this is a pe... 0.6B params. Top3 on MTEB reranking task. 10× smaller than generative listwise rerankers. Read more ... jina-reranker-v3 was the first listwise reranker to throw all documents into one context window (whe... Here's an visualization for jina-embeddings-v4 vectors. This concentration collapses exponents to a ... Find our C implementation: https://t.co/3fT2TIKs0G And the paper: https://t.co/kdwFRBx18L Full paper here: https://t.co/9oWPkIMaW3 Survey on vision encoders in VLMs. The encoder side is weirdly understudied: everyone's busy scaling... Jina-VLM achieves state-of-the-art performance among open 2B-scale VLMs, leading with the highest av... Arxiv: https://t.co/s5Sqt1OkOt HuggingFace: https://t.co/HoUcF87BmJ Blog: https://t.co/0xkZlkEte5 Releasing jina-VLM: our new 2B vision language model achieves SOTA on multilingual visual question a... curl https://t.co/0iNSUvqigB This is our Meta-Prompt. It allows LLMs to understand our Reader, Embed...

Convert your embeddings to spherical coordinates before compression - this trick cuts embedding stor...

Jina AI (@Ji · 2026-01-24 · via Jina AI(@JinaAI_)

此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。原文来自 — 版权归原作者所有。