Hyperspherical Representation Learning

Overview

Hyperspherical representation learning studies how to encode data as directions on a unit sphere, where angles express similarity and embeddings have controlled magnitude. Common approaches include cosine-based contrastive learning, class prototypes, and probability distributions such as von Mises–Fisher, Power Spherical, and Kent models, alongside regularizers that shape the spread of embeddings. These representations are used for image classification and retrieval, anomaly and out-of-distribution detection, generative models, and time-series or multimodal tasks, with evaluations ranging from ImageNet to UCR and UEA benchmarks. A central open question is how to match latent geometry to the data and downstream task: uniformity can aid retrieval and estimation, while concentrated or class-structured embeddings may better preserve semantic distinctions.

Latest papers

CardsList

30 papers3 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

  1. TextSphere: Efficient Text-to-Image Generation via Shared Hyperspherical Alignment and Uniformity

    Nov 17, 2026Yixia Zhang, Girish A. Koushik, Xilu Wang +1T2I GenerationGenerative Modeling

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

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

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

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

  4. Hyperspherical Simplex Representations for Backward-Compatible Retrieval

    Oct 21, 2026Simone Ricci, Niccolò Biondi, Federico Pernici +1Representation LearningHyperspherical Representation Learning

  5. Sphere Encoder 2

    Oct 1, 2026Kaiyu Yue, Sean McLeish, Ruchit Rawal +3AutoencodersImage Generation

  6. Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion

    Sep 21, 2026Mathilde Abrassart, Nicolas Obin, Axel RoebelZero-Shot Voice ConversionNeural Representation Geometry

  7. Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection

    Sep 19, 2026Zhiji Yang, Fangyong Wang, Yue Li +2Semi-Supervised Anomaly DetectionAnomaly Detection

  8. Beyond Gaussian Worlds: Latent Geometry Matters for JEPAs

    Sep 18, 2026Léo Nicollier, Enric Meinhardt-Llopis, Marc Pic +2Joint-Embedding Predictive ArchitectureLatent Space Geometry

  9. CNsEMD: An Expert-Annotated Multi-Field-Strength MRI Dataset and a Hyperspherical Manifold Network for Multimodal Cranial Nerve Parcellation

    Sep 7, 2026Lei Xie, Junxiong Huang, Guoqiang Xie +9Cross-Modality Medical Image SegmentationMedical Image Benchmarks

  10. Absorbing Gradient Conflicts: Modeling Semantic Variance via Kent Distributions for Cross-Modal Hashing

    Aug 25, 2026Hengjie Zhu, Dayan Wu, Zihao Zhang +5Cross-Modal RetrievalGradient Interference

  11. dRAE: Representation Autoencoder with Hyper-Spherical Codes

    Jul 24, 2026Tianren Ma, Lin Long, Chuyan Chen +4AutoencodersHyperspherical Representation Learning

  12. The Hyperspherical Geometry of CLIP Latent Space: A Semantic Mixture Model

    Jul 15, 2026Zijie Yu, Gaowen Liu, Ramana Rao Kompella +2Latent Variable ModelsHyperspherical Representation Learning

  13. Expanding SPHERE-JEPA: A Family of Statistical Regularizers for the Hypersphere

    Jun 16, 2026Léo Nicollier, Enric Meinhardt-Llopis, Max Dunitz +3Maximum Mean DiscrepancyHyperspherical Representation Learning

  14. Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection

    May 29, 2026Willian T. Lunardi, Samridha Shrestha, Martin AndreoniHyperspherical Representation LearningDistribution Shift Detection

  15. SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings

    May 26, 2026L{é}o Nicollier, Max Dunitz, Marc Pic +3Self-Supervised LearningJoint-Embedding Predictive Architecture

  16. Neural Collapse by Design: Learning Class Prototypes on the Hypersphere

    May 19, 2026Panagiotis Koromilas, Theodoros Giannakopoulos, Mihalis A. Nicolaou +1Prototype-Based ClassificationHyperspherical Representation Learning

  17. MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection

    May 11, 2026Yuteng Zhang, Huifang Ma, Jiahui Wei +2Class-Imbalanced LearningSoftware Vulnerability Detection

  18. Polaris: Coupled Orbital Polar Embeddings for Hierarchical Concept Learning

    Apr 30, 2026Sahil Mishra, Srinitish Srinivasan, Sourish Dasgupta +1Hierarchical ClassificationHierarchical Representation Learning

  19. Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces

    Apr 30, 2026Andrew Bond, Ilkin Umut Melanlioglu, Erkut Erdem +1Variational AutoencodersHyperspherical Representation Learning

  20. Hyperspherical Forward-Forward with Prototypical Representations

    Apr 30, 2026Shalini Sarode, Brian Moser, Joachim Folz +4Prototype-Based LearningEfficient Neural Network Inference

  21. Frequency-Aware Semantic Fusion with Gated Injection for AI-generated Image Detection

    Apr 30, 2026Shuchang Zhou, Shangkun Wu, Jiwei Wei +4Hyperspherical Representation LearningAI-Generated Image Detection

  22. Self-Supervised Representation Learning via Hyperspherical Density Shaping

    Apr 27, 2026Esteban Rodríguez-Betancourt, Edgar Casasola-MurilloMulti-View LearningHyperspherical Representation Learning

  23. Neural Precoding in Complex Projective Spaces

    Mar 8, 2026Zaid Abdullah, Merouane Debbah, Symeon Chatzinotas +1Wireless CommunicationsGeometric Representation Learning

  24. Interpretable Maximum Margin Deep Anomaly Detection

    Mar 7, 2026Zhiji Yang, Mei Huang, Xinyu Li +3Semi-Supervised Anomaly DetectionAnomaly Detection

  25. Image Generation with a Sphere Encoder

    Feb 16, 2026Kaiyu Yue, Menglin Jia, Ji Hou +1Image GenerationOne-Step Generative Modeling

  26. SelfGRL: Self-Organized Graph Representation Learning Inspired by Helmholtz Free Energy Minimization

    Dec 30, 2025Rui Chen, Junjun Guo, Hongbin Wang +3Graph Representation LearningGraph SSL

  27. Spherical Cauchy Variational Autoencoders: Heavy Angular Tails and Exact KL Evaluation

    Jun 26, 2025Lukas Sablica, Kurt HornikVariational AutoencodersHyperspherical Representation Learning