6 papers
WinSyn: An Automated Pipeline for Realistic Enterprise Question-Answering Evaluation
Amey Varhade, Ananya Sutradhar, Ravishankar Krishnaswamy +1
Enterprise settings provide a challenging environment for question-answering agents, which often rely on Retrieval-Augmented Generation, Deep Research (DR), and related techniques.…
EigenLI: Spectral Approximations to Late Interaction
Archish S, Sabyasachi Basu, Ankit Garg +2
Late-interaction models such as ColBERT achieve strong effectiveness by representing each document with many token-level vectors, but this expressivity leads to large indexing cost…
Quantization Beyond Uniform Bit Allocation
K. S. Sreeramji, Sabyasachi Basu, Ravishankar Krishnaswamy +2
Quantization is a fundamental technique to handle the growing sizes of embeddings generated by modern models. Existing quantization schemes are largely embedding agnostic and alloc…
Learning Filter-Aware Distance Metrics for Nearest Neighbor Search with Multiple Filters
Ananya Sutradhar, Suryansh Gupta, Ravishankar Krishnaswamy +3
Filtered Approximate Nearest Neighbor (ANN) search retrieves the closest vectors for a query vector from a dataset. It enforces that a specified set of discrete labels for the…
Cost-Effective, Low Latency Vector Search with Azure Cosmos DB
Nitish Upreti, Harsha Vardhan Simhadri, Hari Sudan Sundar +33
Vector indexing enables semantic search over diverse corpora and has become an important interface to databases for both users and AI agents. Efficient vector search requires deep…
Graph-Based Algorithms for Diverse Similarity Search
Piyush Anand, Piotr Indyk, Ravishankar Krishnaswamy +4
Nearest neighbor search is a fundamental data structure problem with many applications in machine learning, computer vision, recommendation systems and other fields. Although the m…