Neural Representation Geometry

Overview

Neural representation geometry asks how learned features are organized by distances, directions, neighborhoods, manifolds, and topology, and how this structure supports prediction, memory, transfer, or behavior. Researchers compare models and brains using methods such as CKA, Procrustes alignment, and relative representations, and characterize spaces with covariance spectra, intrinsic-dimension estimates, persistent homology, and Riemannian geometry; sparse autoencoders and interventions probe feature structure and causal roles. Work spans vision and language models, contrastive embeddings, world models, and neural recordings, with evaluations including retrieval, out-of-distribution transfer, compositional generalization, and brain alignment. A central tension is that measured geometry can change under function-preserving coordinate transformations, while similarity or geometric patterns alone do not establish shared computation, causal importance, or better performance; robust, task-aware measures remain an open need.

Latest papers

CardsList

271 papers18 papers in the last four weeks, down 49% on the four weeks before. 0.1% of all new papers.

  1. Learning to Compare Neural Representations from Parameterized Computation Graphs

    Nov 19, 2026Ya-Wei Eileen Lin, Daniel Herbst, Stefanie JegelkaNeural Representation Geometry

  2. Embedding Cosine Measures Text Length Before It Measures Homogenization

    Nov 16, 2026Fengming Liu, Mingyu ShuText Embedding EvaluationHomogenization in Language Models

  3. Match and Correct: A Repeated Computational Motif in Evoformer Layers

    Nov 13, 2026Ishan Khire, Naren Manikandan, Tyler Hayes +1Protein Structure PredictionNeural Representation Geometry

  4. TetraCoder: Adaptive Tetrahedral Encoding for Neural Fields

    Nov 13, 2026Daniele Della Pietra, Antonella Rech, Nicola Conci +1Neural Representation GeometryNeural Rendering

  5. Representational Geometry as a Diagnostic for Adversarial Robustness

    Nov 13, 2026Brandon Ismalej, Alex Cloninger, Gal MishneAdversarial RobustnessAdversarial Training

  6. Dissecting Geometric Constraints in Grokking: Interaction-Dependent Acceleration in Modular Arithmetic

    Nov 2, 2026Zachary A. Hampton, Wasiq Khan, Bilal KhanGrokkingNeural Representation Geometry

  7. Nonconformal Distortion and Local Orientation Reversal in the Fourier Circuit of a Modular-Addition Transformer

    Oct 30, 2026Eduardo Fuentes, Gonzalo Riera, Héctor Allende-CidNeural Representation GeometryMechanistic Interpretability

  8. Geometric and algebraic inference in humans and neural networks

    Oct 30, 2026Jacob Russin, Joonhwa Kim, Ellie Pavlick +1Logical ReasoningComputational Cognitive Modeling

  9. NeurEO: dissecting Earth observation embeddings with computational neuroscience

    Oct 29, 2026Thijs L van der Plas, Jacob JW Bakermans, Ioannis N AthanasiadisGeospatial Foundation ModelsNeural Representation Geometry

  10. Non-Zero Radius: The Missing Component of Neural Networks

    Oct 29, 2026Tiansi Dong, Mateja Jamnik, Pietro LiòSyllogistic ReasoningLogical Reasoning

  11. The Geometry of Manifold Learning: Singular foliations via Deep Learning models

    Oct 27, 2026Gabriele Novelli, Eliot Tron, Emanuele Latini +1Neural Representation GeometryManifold Learning

  12. Neuronal Identity as an Organizational Basis for Analyzing Neural Population Dynamics

    Oct 27, 2026Seungjae Han, Joshua Yedam You, Soi Kim +5Neural DecodingShared Representation Learning

  13. The Information Geometry of Representation Formation

    Oct 25, 2026Sanjukta KrishnagopalNeural Representation GeometryInformation Geometry

  14. Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data

    Oct 23, 2026Joonhyeok Jeong, Jy-yong Sohn, Kibok LeeContrastive LearningSupervised Contrastive Learning

  15. The Geometry of Meaning in Neural Manifolds

    Oct 22, 2026Valentino MaiorcaNeural Representation GeometrySemantic Correspondence

  16. Learning the Geometry of Materials Space with Trained Neural Tangent Kernels

    Oct 20, 2026Daniel Kaplan, Gabriel Kotliar, Anirvan M SenguptaNeural Representation GeometryComputational Materials Science

  17. Spherical Fixed-Point Reasoners: Adaptive Loop Halting on the Hypersphere

    Oct 19, 2026Arber Zela, Artavazd Maranjyan, Pol Puigdemont +3Adaptive Reasoning in Language ModelsStructured Reasoning in Language Models

  18. Multilingual Brain Decoding Reveals Shared Cortical Semantic Geometry

    Oct 17, 2026Yi Guo, Yong Hu, Michael Kwok-Po Ng +1Cross-Lingual Representation AlignmentNeural Representation Geometry

  19. Representations Have Trajectories: Characterizing Temporal Representation Dynamics in Neural Networks

    Oct 17, 2026Shivaprasad B. Gowda, Sparsh MittalLow-Rank Representation LearningNeural Representation Geometry

  20. Escaping Parameter Space: Tight Generalization Bounds via Representation Quality

    Oct 16, 2026Niclas Göring, Shuofeng Zhang, Branton DeMoss +1Generalization BoundsNeural Representation Geometry

  21. A Topological Signature of Learning under Noisy Labels

    Oct 16, 2026Zhongtian Sun, Fan Mo, Prayag Tiwari +1Noisy-Label LearningNeural Representation Geometry

  22. Learning to Be Guided: Shaping Latent Geometry for Classifier-Free Guidance

    Oct 16, 2026Haoming Liu, Junhao Zhu, Shaoyi Zheng +4Latent Space GeometryDiffusion-Based Image Generation

  23. Native Geometry vs. Linear Recoverability: How Alignment Changes Platonic Scaling

    Oct 15, 2026Angus Hoy, Austin Lutterbach, Jasper Chong +2Neural Representation GeometryLatent Space Geometry

  24. A Closed Form Depth-Width Law for Neural Collapse in Deep Linear Networks

    Oct 15, 2026Pankhil Gawade, Kirsten Fischer, Guy Wolf +1Neural Representation GeometryNeural Scaling Laws

  25. A Phenomenology of Neural Geometry in Vision-Language-Action Models

    Oct 14, 2026Mozes Jacobs, Aiden Swann, Mathilde Papillon +16Neural Representation GeometryVision-Language-Action Models

  26. Order-Consistent Latent Geometry for Reliable Short-Horizon Planning in World Models

    Oct 13, 2026Junlin Wu, Wen Fan, Dandan ZhangLatent Space GeometryLatent-Space Planning

  27. Geometric Structure Predicts Per-Example Neighborhood Loss Under PCA Truncation

    Oct 13, 2026Sriram Loganathan, Gokul Anand, Ragavan ArivazhaganText Embedding EvaluationEmbedding Compression