The Excellence
Directory Platform Template

Sparse Late Interaction Retrieval model that combines the benefits of sparse representations with late interaction mechanisms. Provides efficient storage and fast retrieval while maintaining the accuracy advantages of token-level matching in sparse embedding space.

Advanced vector quantization technique that explores the Leech lattice's optimal sphere packing properties at 24 dimensions. Delivers state-of-the-art LLM quantization performance, outperforming recent methods like Quip#, QTIP, and PVQ for extreme vector compression.

Fast and accurate graph-based ANN index for streaming similarity search, enabling real-time updates on billion-point indexes using a single machine with real-time freshness.

Low-Rank Matrix Factorization algorithm for Approximate Nearest Neighbor Search, offering competitive performance with faster query times than leading libraries at various recall levels.

Parallel Efficient Clustering with graph-based Approximate Nearest Neighbor search, providing efficient clustering algorithms optimized for high-dimensional vector spaces.

Distributed disk-based approximate nearest neighbor system achieving near-linear throughput scaling. Delivers 6.21-6.49x throughput improvement over scatter-gather baseline with sub-6ms latency on 10 servers.

Manifold-Consistent Graph Indexing for billion-scale disk-resident vector search. Leverages Local Intrinsic Dimensionality to achieve 5.8x throughput improvement over DiskANN on high-dimensional datasets.

Incremental in-place update system for billion-scale vector search from Microsoft Research. Maintains 2.41x lower P99.9 latency than baselines while supporting efficient vector updates with minimal resource overhead.

Efficient multi-vector retrieval system using sparsified late interaction with inverted indexes. Achieves 40% less storage and 83% lower latency than ColBERT-v2 while maintaining competitive accuracy.

AiSAQ is an all-in-storage approximate nearest neighbor search system that uses product quantization to enable DRAM-free vector similarity search, serving as a specialized vector search/indexing approach for large-scale information retrieval.

DET-LSH is a locality-sensitive hashing scheme that introduces a dynamic encoding tree structure to accelerate approximate nearest neighbor (ANN) search in high-dimensional spaces. While it is a research algorithm rather than a production database, it directly targets the core operation behind vector databases—efficient ANN search over vector embeddings—and is relevant for designing or optimizing vector indexing components within vector database systems.

GTS is a GPU-based tree index for fast similarity search over high-dimensional vector data, providing an efficient ANN index structure that can be integrated into or used to build high-performance vector database systems.