3 papers
cs.IR2026
Breaking the Curse of Dimensionality: On the Stability of Modern Vector Retrieval
Vihan Lakshman, Blaise Munyampirwa, Julian Shun +1
Modern vector databases enable efficient retrieval over high-dimensional neural embeddings, powering applications from web search to retrieval-augmented generation. However, classi…
cs.SD2025
SDBench: A Comprehensive Benchmark Suite for Speaker Diarization
Eduardo Pacheco, Atila Orhon, Berkin Durmus +2
Even state-of-the-art speaker diarization systems exhibit high variance in error rates across different datasets, representing numerous use cases and domains. Furthermore, comparin…
cs.LG2025
Down with the Hierarchy: The 'H' in HNSW Stands for "Hubs"
Blaise Munyampirwa, Vihan Lakshman, Benjamin Coleman
Driven by recent breakthrough advances in neural representation learning, approximate near-neighbor (ANN) search over vector embeddings has emerged as a critical computational work…