arXiv AI
When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task
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 10
Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
arXiv:2609.05575v1 Announce Type: new Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability,...
arXiv Machine Learning
Jul 1
Low-dimensional topology of deep neural networks
arXiv:2606. 31856v1 Announce Type: new Abstract: We study layered models, including feedforward networks, ResNets, and transformers, by limiting each layer to a width of $d = 3$, i.
arXiv Machine Learning
Jul 7
Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models
arXiv:2602. 24264v2 Announce Type: replace-cross Abstract: Compositional generalization, the ability to recognize familiar parts in novel contexts, is a defining property of intelligent systems.
arXiv Machine Learning
Jul 13
How are linear representations learned? Exact solutions to the dynamics of abstraction
arXiv:2607. 08843v1 Announce Type: new Abstract: In artificial and biological neural networks, concepts are often encoded as consistent linear directions in representation space.
arXiv AI
Jun 2
Emergent Ordinal Geometry in Transformers Trained on Local Comparisons
arXiv:2606. 01269v1 Announce Type: new Abstract: Transitive inference is the challenge of inferring that A < C from knowing only adjacent relations (A < B, B < C).
arXiv AI
Jul 14
Laguerre Geometry for Interpreting Large Language Models
arXiv:2607. 10578v1 Announce Type: new Abstract: Existing hypotheses represent a concept in an LLM as a single point, a linear direction, or a Gaussian cluster, yet it remains unclear how and why such structures emerge.