jina-embeddings-v5-text Collection Our 5th-gen embeddings: two lightweight multilingual models with SOTA performance in retrieval, matching, clustering, and classification. • 29 items • Updated 13 days ago • 35
view article Article LateOn-Code & ColGrep: LightOn unveils state-of-the-art code retrieval models and code search tooling 28 days ago • 49
view article Article Community Evals: Because we're done trusting black-box leaderboards over the community +5 Feb 4 • 88
view article Article 🪄 Interpreto: A Unified Toolkit for Interpretability of Transformer Models Jan 20 • 37
Does It Tie Out? Towards Autonomous Legal Agents in Venture Capital Paper • 2512.18658 • Published Dec 21, 2025 • 11
OmniVinci: Enhancing Architecture and Data for Omni-Modal Understanding LLM Paper • 2510.15870 • Published Oct 17, 2025 • 91
ModernVBERT: Towards Smaller Visual Document Retrievers Paper • 2510.01149 • Published Oct 1, 2025 • 33
When Does Reasoning Matter? A Controlled Study of Reasoning's Contribution to Model Performance Paper • 2509.22193 • Published Sep 26, 2025 • 38
view article Article When Does Reasoning Matter? Unpacking the Contribution of Reasoning to LLM Performance Sep 30, 2025 • 12
mmBERT: A Modern Multilingual Encoder with Annealed Language Learning Paper • 2509.06888 • Published Sep 8, 2025 • 12