Tag
The paper introduces WETW, a learned pair-specific weighted Euclidean distance for efficient Dynamic Time Warping (DTW) similarity search, plus the WESee encoder, achieving 11.4x speedup over exact baselines with 0.93 mean recall@10 across eight datasets.
The article explores how splitting tasks across conversation turns reduces agent accuracy and proposes a memory system using context-specific retrieval types to maintain accuracy, with a hands-on example using the open-source Graphiti engine.
Educational article explaining FAISS, a library for billion-scale similarity search, covering vector embeddings, nearest neighbor search, and techniques like IVF and Product Quantization for efficient retrieval.
Tomesphere is a free tool that enriches arXiv and OpenAlex paper pages with Gemini-generated TLDRs, peer reviews, code repos, and a SPECTER2 similarity graph for discovery.
Alibaba releases Zvec v0.5.0, an open-source in-process vector database with new features including full-text search, hybrid retrieval, DiskANN index, and new SDKs for Go, Rust, plus a visual tool.