Muvera: Making multi-vector retrieval as fast as single-vector search(research.google)89 points by georgehill 1 year ago | 7 comments
Upgrading DrizzleORM logging with AsyncLocalStorage(numeric.substack.com)25 points by bihla 9 months ago | 3 comments
Matryoshka Representation Learning with CLIP(marqo.ai)25 points by esleightholm 2 years ago | 0 comments
V-JEPA 2 world model and new benchmarks for physical reasoning(ai.meta.com)281 points by mfiguiere 1 year ago | 88 comments
Nixiesearch: Running Lucene over S3, and why we're building a new search engine(nixiesearch.substack.com)102 points by shutty 2 years ago | 65 comments
Fixed three bugs that made Qwen3.5-122B a daily driver on Mac Studio(mrzk.io)55 points by marzukia 3 months ago | 22 comments
