- 1 Bootstrapping Audio Embeddings from Multimodal LLMs ↗
- 2 Identifying Embedding Models from Raw Numerical Values ↗
- 3 jina-embeddings-v5-text: New SOTA Small Multilingual Embeddings ↗
- 4 Jina-VLM: Small Multilingual Vision Language Model ↗
- 5 Jina Reranker v3: 0.6B Listwise Reranker for SOTA Multilingual Retrieval ↗
- 6 Embeddings Are AI’s Red-Headed Stepchild ↗
- 7 Multimodal Embeddings in Llama.cpp and GGUF ↗
- 8 Jina Code Embeddings: SOTA Code Retrieval at 0.5B and 1.5B ↗
- 9 Agentic Workflow with Jina Remote MCP Server ↗
- 10 Optimizing GGUFs for Decoder-Only Embedding Models ↗
- 11 What We Learned at SIGIR 2025 ↗
- 12 How Image Resolution Impacts Visual Document Retrieval ↗
- 13 JinaVDR: New Visual Document Retrieval Benchmark with 95 Tasks in 20 Languages ↗
- 14 Submodular Optimization for Text Selection, Passage Reranking & Context Engineering ↗
- 15 Submodular Optimization for Diverse Query Generation in DeepResearch ↗