Proposes Unified Dominance Graph (UDG) for interval-predicate ANNS by mapping to dominance space and building a predicate-specific graph index with patch edges for better search under filters.
Approximate nearest neighbors: tow ards removing the curse of dimensionality
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
A per-component SimHash fingerprint supplies structural identity for AI agent skills, recovering family membership under paraphrase and refactoring with AUC 0.974 while localizing changes.
SelfCompact pairs a model-invoked compaction tool with a lightweight rubric to enable adaptive context management in LM agents, achieving efficiency gains over fixed-interval baselines.
Large-scale HPC evaluation of Qdrant, Milvus, and Weaviate reveals that workload patterns limit scaling and extra cores can reduce throughput, exposing a cloud-to-HPC design mismatch.
ANN search quality is better assessed by 1/Ratio@k than Recall@k because the former tracks downstream task utility more closely while allowing substantially lower computational cost.
Introduces a sketch-based watermarking method for masked diffusion language models providing an order-agnostic detection statistic decoupled from local context.
ULPT optimizes prompts in ultra-low dimensions with frozen random up-projection to cut training parameters by 98% while matching vanilla prompt tuning performance on NLP tasks.
A pipeline using product quantization and systematic parameter evaluation creates data-driven soil taxonomies with higher specificity than human-derived classifications.
Dask parallelization of product quantization and inverted indexing allows large-scale approximate nearest neighbor search while preserving accuracy and reducing computation to medium-scale levels.
The paper analyzes participant opinions from a Physics of Life Reviews discussion on the simplicity revolution in high-dimensional neuroscience and its implications for machine learning.
citing papers explorer
-
Symphony of high-dimensional brain
The paper analyzes participant opinions from a Physics of Life Reviews discussion on the simplicity revolution in high-dimensional neuroscience and its implications for machine learning.