NAACA uses a neuro-inspired oscillatory working memory to gate attention in audio language models, raising AudioQwen's average precision from 53.5% to 70.6% on XD-Violence while cutting unnecessary calls.
International conference on database theory , pages=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
years
2026 5verdicts
UNVERDICTED 5representative citing papers
Common ID estimators fail to track the true intrinsic dimension of neural representations and are instead driven by other factors.
Multiscale CMH scanning generalizes the classic test to continuous spaces, achieving consistency for conditional independence testing by conditioning on marginal order statistics without requiring large stratum sizes.
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.
citing papers explorer
-
NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
NAACA uses a neuro-inspired oscillatory working memory to gate attention in audio language models, raising AudioQwen's average precision from 53.5% to 70.6% on XD-Violence while cutting unnecessary calls.
-
Rethinking Intrinsic Dimension Estimation in Neural Representations
Common ID estimators fail to track the true intrinsic dimension of neural representations and are instead driven by other factors.
-
Multiscale Cochran-Mantel-Haenszel Scanning for Conditional Dependency
Multiscale CMH scanning generalizes the classic test to continuous spaces, achieving consistency for conditional independence testing by conditioning on marginal order statistics without requiring large stratum sizes.
-
Position: Uncertainty Quantification in LLMs is Just Unsupervised Clustering
Mainstream UQ for LLMs reduces to unsupervised clustering of internal generation consistency and therefore cannot detect confident hallucinations or provide reliable safety signals.
-
Robustness Analysis of USmorph: II. Optimizing Feature Extraction, Dimensionality Reduction, and Clustering for Unsupervised Galaxy Morphology Classification
Optimizes ImageNet-pretrained AlexNet, UMAP, and a bagging multi-cluster voting scheme with K-means, Birch and Agg for unsupervised galaxy morphology classification, reporting improved stability and consistency with galaxy evolution expectations.