No article text was recorded for this version.
geometric interpretability
Version 1 of 137 papers39 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Neural Feature Geometry Evolves as Discrete Ricci Flow
- Blog: A singular Riemannian geometry approach to Deep Neural Networks I. Theoretical foundations
- Blog: Embed Me If You Can: A Geometric Perceptron
- Blog: Comparing Optimization Targets for Contrast-Consistent Search
- Blog: Deep Networks as Paths on the Manifold of Neural Representations
- Blog: Denoising for Manifold Extrapolation
- Blog: The Geometry of Tokens in Internal Representations of Large Language Models
- Blog: Low Rank Structure of Learned Representations
- Blog: Intrinsic dimension of data representations in deep neural networks
- Blog: Metric Flows with Neural Networks
- Blog: Functional Properties of PDE-Based Group Equivariant Convolutional Neural Networks
- Blog: Constrained Belief Updates Explain Geometric Structures in Transformer Representations
- Blog: Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs
- Blog: Unveiling Transformer Perception by Exploring Input Manifolds
- Blog: Editorial: Symmetry as a guiding principle in artificial and brain neural networks
- Blog: The Star Geometry of Critic-Based Regularizer Learning
- Blog: Efficient Representation of Low-Dimensional Manifolds using Deep Networks
- Blog: Geodesics of learned representations Olivier Hénaff
- Blog: Learning Diverse and Discriminative Representations via the Principle of Maximal Coding Rate Reduction
- Blog: Experimental Observations of the Topology of Convolutional Neural Network Activations
- Blog: Emergence of Separable Manifolds in Deep Language Representations
- Blog: Untangling in Invariant Speech Recognition
- Blog: Neural Networks Trained to Solve Differential Equations Learn General Representations
- Blog: Harmonic Loss Trains Interpretable AI Models
- Blog: Parametric Shape Modeling and Skeleton Extraction With Radial Basis Functions Using Similarity Domains Network
- Blog: Approximating Latent Manifolds in Neural Networks via Vanishing Ideals
- Blog: How Data Augmentation Shapes Neural Representations
- Blog: Deep Self-expressive Learning
- Blog: Sigma Flows for Image and Data Labeling and Learning Structured Prediction
- Blog: Principles of Riemannian Geometry in Neural Networks
- Blog: Data Representations' Study of Latent Image Manifolds
- Blog: Exponential expressivity in deep neural networks through transient chaos
- Blog: Separability and geometry of object manifolds in deep neural networks
- Blog: Feature Learning beyond the Lazy-Rich Dichotomy: Insights from Representational Geometry
- Blog: Fine-Tuned Transformers Show Clusters of Similar Representations Across Layers
- Blog: Curvature-based Comparison of Two Neural Networks
- Blog: Centroid Affinity: How Deep Networks Represent Features
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_geometric_interpretability_61fd0d96,
title = {geometric interpretability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/geometric-interpretability/rdr_61fd0d9604ae450b9591ffd281107bb9},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_geometric_interpretability_61fd0d96_v1,
title = {geometric interpretability},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/geometric-interpretability/rdr_61fd0d9604ae450b9591ffd281107bb9/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}