collaborators

5 papers

cs.LG2026

PROTOCOL: Late Interaction Retrieval for Protein Homolog Search

Gabrielle Cohn, Rohan Gumaste, Minh Hoang +1

Protein homology search underlies function annotation, structure prediction, and evolutionary analysis, but remains challenging in the "twilight zone," where global sequence simila…

cs.DS2026

CARAMEL: A Succinct Read-Only Lookup Table via Compressed Static Functions

Benjamin Coleman, David Torres Ramos, Vihan Lakshman +2

Lookup tables are a fundamental structure in many data processing and systems applications. Examples include tokenized text in NLP, quantized embedding collections in recommendatio…

cs.DS2026

AutoCSF: Provably Space-Efficient Indexing of Skewed Key-Value Workloads via Filter-Augmented Compressed Static Functions

David Torres Ramos, Vihan Lakshman, Chen Luo +2

We study the problem of building space-efficient, in-memory indexes for massive key-value datasets with highly skewed value distributions. This challenge arises in many data-intens…

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.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…