FlyHash tested for LLM agent memory; quality holds, savings do not
Matched-bit tests beat SimHash on neighbor quality, but HNSW is smaller and faster at ordinary scale.
Stories per day · 30 days
4 RSS
Relatedagent-memory1ai-security1flyhash1ivfflat1llm1llm-agents1locality-sensitive-hashing1pgvector1poisoning1postgresql1rag1retrieval1timescale1vector-search1wikipedia1
6 stories, newest first · one card per story
Stories tagged #hnsw
Poisoning the Neighborhood: A Topology-Aware Topic-Level Attack on Large-Scale HNSW-based RAG Systems
Researchers demonstrate a Hub-Satellite poisoning attack on HNSW RAG with 31.29% success on two million Wikipedia documents.
Pg_vectorsearch: An index that is faster than pgvector's IVFFlat and HNSW
Timescale's pg_vectorsearch claims a PostgreSQL vector index faster than pgvector IVFFlat and HNSW.
Better Vector Search for Long Documents: Chunking Inside Manticore Search
Manticore Search added automatic document chunking for vector columns, lifting long-document recall@5 from 55.1% to 83.3% in its benchmarks.
3
Atlas: Efficient Verifiable Semantic Search
Atlas delivers zero-knowledge proofs for HNSW semantic search, verifying RAG retrieval in under a second on SIFT1M and 2.0 seconds at 100M vectors.
Hoss: Fast Oblivious Semantic Search with Heterogeneous GPU-CPU-TEE Architecture
Hoss uses heterogeneous GPU-CPU TEEs for oblivious semantic search, achieving up to 67x speedup over the Compass ORAM-based system.