Tech

How Image Resolution Impacts Visual Document Retrieval

Traditional computer vision models typically focus on mimicking human visual perception. jina-embeddings-v4 takes a different approach: it combines image and text processing to understand how people read and interpret information presented visually. Unlike OCR programs that simply digitize text, it actually parses complex visual materials like infographics, charts, diagrams, and tables—documents where both the text and visual elements carry semantic meaning. We call these "visually rich documents."

Errors found in US judge’s withdrawn decision stink of AI

Posts from this topic will be added to your daily email digest and your homepage feed.

Amazon buys Bee AI wearable that listens to everything you say

Posts from this topic will be added to your daily email digest and your homepage feed.

Adobe's New AI Tool Turns Silly Noises into Realistic Audio Effects

Posts from this topic will be added to your daily email digest and your homepage feed.

Jina Embeddings v4: Universal Embeddings for Multimodal Multilingual Retrieval

Today we're releasing jina-embeddings-v4, our new 3.8 billion parameter universal embedding model for text and images. It includes a set of task-specific LoRA adapters that optimize performance for the most popular retrieval tasks, including query-document retrieval, semantic matching, and code search. jina-embeddings-v4 achieves state-of-the-art retrieval performance on multimodal and multilingual tasks across MTEB, MMTEB, CoIR, LongEmbed, STS, Jina-VDR, CLIP, and ViDoRe benchmarks, with particular strength in processing visually rich content such as tables, charts, diagrams, and mixture of them. The model supports both single-vector and multi-vector embeddings.

Microsoft’s LinkedIn chief is now running Office as part of an AI reorg

Posts from this topic will be added to your daily email digest and your homepage feed.

Google will let you ‘try on’ clothes with AI

Posts from this topic will be added to your daily email digest and your homepage feed.

Microsoft is now hosting xAI’s Grok 3 models

Posts from this topic will be added to your daily email digest and your homepage feed.

Mexico is suing Google over how it’s labeling the Gulf of Mexico

Posts from this topic will be added to your daily email digest and your homepage feed.

Anthropic launches research tool and Google Workspace integration

Posts from this topic will be added to your daily email digest and your homepage feed.

A Radical New Proposal For How Mind Emerges From Matter

If we could stop bickering about which creatures do or don’t deserve to be called smart, an emerging movement of scientists and philosophers argue that we might discover fundamental elements of intelligence that are common to all life.

Amazon to invest another $4 billion in OpenAI rival Anthropic

Posts from this topic will be added to your daily email digest and your homepage feed.