Pressemitteilungen

jina-reranker-v3.5: An Efficient Listwise Reranker with Hybrid Attention and Self-Distillation

jina-embeddings-v5-omni: Geometry-preserving Embeddings via Locked Aligned Towers

jina-embeddings-v5-text: Task-Targeted Embedding Distillation

Embedding Compression via Spherical Coordinates

Vision Encoders in Vision-Language Models: A Survey

Jina-VLM: Small Multilingual Vision Language Model

jina-reranker-v3: Last but Not Late Interaction for Document Reranking

Efficient Code Embeddings from Code Generation Models

jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval

ReaderLM-v2: Small Language Model for HTML to Markdown and JSON

AIR-Bench: Automated Heterogeneous Information Retrieval Benchmark

jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images

jina-embeddings-v3: Multilingual Embeddings With Task LoRA

Late Chunking: Contextual Chunk Embeddings Using Long-Context Embedding Models

Jina-ColBERT-v2: A General-Purpose Multilingual Late Interaction Retriever

Leveraging Passage Embeddings for Efficient Listwise Reranking with Large Language Models

Jina CLIP: Your CLIP Model Is Also Your Text Retriever

Multi-Task Contrastive Learning for 8192-Token Bilingual Text Embeddings

Jina Embeddings 2: 8192-Token General-Purpose Text Embeddings for Long Documents

Jina Embeddings: A Novel Set of High-Performance Sentence Embedding Models