A developer built Clean Air Window, a Streamlit app that uses Google's open-weight Gemma 4 31B model through OpenRouter to pick the cleanest hour for outdoor activity in smog-prone cities. The tool-ca…
Qdrant researchers found that multilingual embedding models group text by language as well as meaning, causing same-language answers to appear in the top 10 in 61% of cases on the 15,277-article, five…
A developer has released EmbedFlow, an open-source tool that enables zero-downtime upgrades of embedding models by retrieving top-K documents with the old model and reranking them with the new model, …
Independent researcher Jason Van Pham released a preprint on 27 August 2026 proposing a method to translate continuous representations between frozen AI models, enabling sign-sensitive semantic invers…
Google Cloud has introduced native vLLM TPU support for embedding inference, targeting production long-context retrieval with Qwen3-Embedding-8B and Qwen3-VL-Embedding-8B. The engineering effort addre…
SplatRAG 3, a retrieval system using local Gaussian-splat memory, achieved a SciFact (BEIR test, 300 claims, k=10) recall@10 of 0.8804 and nDCG@10 of 0.7624 on a store that also contains 5,000 Urban D…
Databricks has developed a hybrid approach combining AI Classify with vector search that outperforms frontier models on accuracy and cost for document classification tasks involving taxonomies of 100,…
OpenAI's text-embedding-3-large embedding model has fallen to 13th place out of 15 on the 2026 aggregate embedding leaderboard with a score of 58.96, while the free, Apache 2.0-licensed Qwen3-Embeddin…
Researchers introduced Refine Thought (RT), a method that enhances text embedding models by executing multiple forward passes to improve semantic reasoning. RT significantly boosted performance on spe…