2 papers
cs.CL2026
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Mohammad Kalim Akram, Saba Sturua, Nastia Havriushenko +4
Text embedding models are widely used for semantic similarity tasks, including information retrieval, clustering, and classification. General-purpose models are typically trained w…
cs.AI2025
jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval
Michael Günther, Saba Sturua, Mohammad Kalim Akram +8
We introduce jina-embeddings-v4, a 3.8 billion parameter multimodal embedding model that unifies text and image representations through a novel architecture supporting both single-…