News
Accelerate search AI, one token at a time.
Featured
jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation
Explains the v3.5 architecture, distillation approach, and its role in document reranking.
· 11 min read
jina-embeddings-v5-omni: Embeddings for Text, Image, Audio and Video
Introduces the v5-omni family and its shared representations across four input modalities.
· 7 min read
jina-embeddings-v5-text: New SOTA Small Multilingual Embeddings
Presents two v5-text model sizes and deployment options for multilingual retrieval.
· 7 min readImages: Jina AI / original publishers
Academic Publications
jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation
SIGIR 2026jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers
SIGIR 2026jina-embeddings-v5-text: Task-Targeted Embedding Distillation
ICLR 2026Embedding Compression via Spherical Coordinates
arXivVision Encoders in Vision-Language Models: A Survey
ICLR 2026Jina-VLM: Small Multilingual Vision Language Model
AAAI 2026jina-reranker-v3: Last but Not Late Interaction for Document Reranking
NeurIPS 2025Efficient Code Embeddings from Code Generation Models
EMNLP 2025jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
ICLR 2025ReaderLM-v2: Small Language Model for HTML to Markdown and JSON
ACL 2025AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark
ICLR 2025jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images
ECIR 2025jina-embeddings-v3: Multilingual Embeddings With Task LoRA
SIGIR 2025Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models
EMNLP 2024Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever
WWW 2025Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models
ICML 2024Jina CLIP: Your CLIP Model Is Also Your Text Retriever
arXivMulti-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings
arXivJina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents
EMNLP 2023Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models
Original page 1 of 10 · Articles 1–10
jina-reranker-v3.5: Faster Listwise Reranking with Hybrid Attention and Self-Distillation
Explains the v3.5 architecture, distillation approach, and its role in document reranking.
jina-embeddings-v5-omni: Embeddings for Text, Image, Audio and Video
Introduces the v5-omni family and its shared representations across four input modalities.
Bootstrapping Audio Embeddings from Multimodal LLMs
Examines how multimodal generative models can be adapted into audio encoders for retrieval.
Identifying Embedding Models from Raw Numerical Values
Investigates whether numerical vector patterns can reveal which embedding model produced them.
jina-embeddings-v5-text: New SOTA Small Multilingual Embeddings
Presents two v5-text model sizes and deployment options for multilingual retrieval.
Jina-VLM: Small Multilingual Vision Language Model
Introduces a vision-language model designed for multilingual visual question answering.
Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval
Explains how v3 compares candidate documents jointly for relevance ranking.
Multimodal Embeddings in Llama.cpp and GGUF
Covers engineering lessons from adding multimodal embedding support to llama.cpp and GGUF.
Jina Code Embeddings: SOTA Code Retrieval at 0.5B and 1.5B
Introduces two code-encoder sizes and the retrieval tasks they support.
Agentic Workflow with Jina Remote MCP Server
Shows how remote MCP connects search and reading tools to agent workflows.
This collection includes the first and last pages of the source newsroom. Search and filters apply to these articles. Explore the full newsroom