arXiv AI
Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation Audits
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Sep 21
COMPLEX: A Closed-Form Certified Embedding of Multiparameter Persistence Modules
COMPLEX is a closed‑form, training‑free embedding for multiparameter persistence modules that provides both an upper and a lower Lipschitz bound, enabling faithful feature representations. By slicing modules along a near‑diagonal net and embedding each slice with the certified PLACE/PALACE landmark map, the method guarantees that separated modules remain separated in the embedding. On Orbit benchmarks and molecular graph tasks, COMPLEX achieves state‑of‑the‑art accuracy, outperforming existing landmark, transformer, and graph‑based approaches.
arXiv Machine Learning
Sep 22
When and Why Do Linear Bias Probes Fail? A Geometric and Statistical Theory of Bias Detectability in Large Language Model Representations
arXiv:2609.22337v1 Announce Type: cross Abstract: Linear probing is the standard instrument for detecting social biases in the hidden representations of large language models. Yet reported probe accu...
arXiv Machine Learning
Jul 3
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
arXiv:2606. 13092v3 Announce Type: replace Abstract: Scale buys interpolation; structure buys certifiable transfer.
arXiv Machine Learning
Jun 25
Conformal Orbit-Valid Trust Horizons for Equivariant World Models
arXiv:2606. 24946v1 Announce Type: new Abstract: Learned world models are useful only over horizons on which their rollout error remains controlled.
arXiv AI
Jun 2
UR-JEPA: Uniform Rectifiability as a Regularizer for Joint-Embedding Predictive Architectures
arXiv:2606. 01443v1 Announce Type: cross Abstract: A central difficulty in training Joint-Embedding Predictive Architectures (JEPAs) is preventing representation collapse.
arXiv Machine Learning
Jul 28
When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction
arXiv:2607. 24662v1 Announce Type: new Abstract: Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap.