ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 3
citation-polarity summary
years
2026 4verdicts
UNVERDICTED 4roles
background 3polarities
background 3representative citing papers
MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
BBC improves large-k ANN efficiency via bucketed candidate buffers and optimized re-ranking, delivering up to 3.8x speedup at recall@k=0.95.
A Voronoi cell estimation framework in embedding space enables principled token pruning for late-interaction models, reducing index size while retaining retrieval quality.
citing papers explorer
-
Visual Late Chunking: An Empirical Study of Contextual Chunking for Efficient Visual Document Retrieval
ColChunk adaptively chunks visual document patches into contextual multi-vectors via clustering, cutting storage by over 90% while raising average nDCG@5 by 9 points.
-
Unified and Efficient Approach for Multi-Vector Similarity Search
MV-HNSW is the first native hierarchical graph index for multi-vector data, achieving over 90% recall with up to 14x lower search latency than prior filter-and-refine approaches across seven datasets.
-
BBC: Improving Large-k Approximate Nearest Neighbor Search with a Bucket-based Result Collector
BBC improves large-k ANN efficiency via bucketed candidate buffers and optimized re-ranking, delivering up to 3.8x speedup at recall@k=0.95.
-
A Voronoi Cell Formulation for Principled Token Pruning in Late-Interaction Retrieval Models
A Voronoi cell estimation framework in embedding space enables principled token pruning for late-interaction models, reducing index size while retaining retrieval quality.