Guardrail classifiers receive formal guarantees by certifying convex harmful regions in pre-activation space, exposing safety holes in three toxicity models despite high empirical scores.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4verdicts
UNVERDICTED 4representative citing papers
Soft-MSM is a smooth, gradient-enabled version of the context-aware MSM distance for time series alignment that outperforms Soft-DTW alternatives in clustering and nearest-centroid classification.
GTSA-PCA replaces global PCA covariance with curvature-weighted local operators and a geodesic alignment step to produce geometry-aware embeddings that improve on standard PCA and UMAP in small-sample high-curvature settings.
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
-
Beyond Red-Teaming: Formal Guarantees of LLM Guardrail Classifiers
Guardrail classifiers receive formal guarantees by certifying convex harmful regions in pre-activation space, exposing safety holes in three toxicity models despite high empirical scores.
-
Soft-MSM: Differentiable Context-Aware Elastic Alignment for Time Series
Soft-MSM is a smooth, gradient-enabled version of the context-aware MSM distance for time series alignment that outperforms Soft-DTW alternatives in clustering and nearest-centroid classification.
-
Curvature-Aware PCA with Geodesic Tangent Space Aggregation for Semi-Supervised Learning
GTSA-PCA replaces global PCA covariance with curvature-weighted local operators and a geodesic alignment step to produce geometry-aware embeddings that improve on standard PCA and UMAP in small-sample high-curvature settings.
-
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.