Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input embeddings.
Dimensionality compression and expansion in deep neural networks
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
Empirical analysis of sequential ResNet-18 training on Split CIFAR-100 finds stable recovery subspace dimensionality supporting the Stable Recovery Manifold hypothesis that forgotten knowledge remains compactly decodable.
citing papers explorer
-
Formalizing Latent Thoughts: Four Axioms of Thought Representation in LLMs
Four axioms (Causality, Minimality, Separability, Stability) are formalized for latent thought representations; audits of open LLMs on 23 tasks show none satisfy all four and representations add little beyond input embeddings.
-
Intermediate Representations are Strong AI-Generated Image Detectors
Intermediate layer embedding sensitivity to perturbations distinguishes AI-generated images from real ones, yielding higher AUROC on GenImage and Forensics Small benchmarks than prior methods.
-
The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning
Empirical analysis of sequential ResNet-18 training on Split CIFAR-100 finds stable recovery subspace dimensionality supporting the Stable Recovery Manifold hypothesis that forgotten knowledge remains compactly decodable.