Geometric Representation Learning

Overview

The field studies how to represent data whose structure is not well described by ordinary flat vectors, including point clouds, graphs, molecules, shapes, and signals. Approaches include rotation- and group-equivariant networks, learning directly on Riemannian, spherical, or hyperbolic spaces, and using geodesic distances, curvature, or spectral structure to guide training. These methods aim to preserve meaningful geometry so models can generalize across changes in viewpoint, sampling, or domain, with applications from 3D perception and robotics to biology and medical imaging. A central challenge is choosing geometry that fits the task: explicit geometric constraints can improve robustness and data efficiency, but may add computational cost or hinder downstream learning when the chosen structure is mismatched.

Latest papers

CardsList

268 papers16 papers in the last four weeks, down 58% on the four weeks before. 0.1% of all new papers.

  1. ViGA-FLAME: Aligning Latent Visual and Geometric Representations for Robust 3D Head Expression Estimation

    Nov 10, 2026Wen Hao He, Jiacheng Wu, Jie Chen3D Face ReconstructionGeometric Representation Learning

  2. Controlled Binary Assignment Flows

    Nov 9, 2026Paul Fröhling, Christoph SchnörrGeometric Representation LearningGraph-Based Semi-Supervised Learning

  3. A Geometry-Guided Feature-Space Framework for Interpretable Unsupervised 4D-STEM Analysis of Complex Multiphase Materials

    Nov 7, 2026Arda Genc, Daniel A. Bolden, Albert Nguyen +2Unsupervised ClusteringScanning Transmission Electron Microscopy

  4. GEKey: Learning Geodesic Eccentric 3D Keypoints via Self-Supervision

    Nov 5, 2026Pierre Onghena, Santiago Velasco-Forero, Beatriz MarcoteguiKeypoint DetectionSelf-Supervised Point Cloud Learning

  5. Geometric Morphology Learning: Empowering Foundation Models from Structure to Spacetime Intelligence

    Nov 1, 2026Li Sun, Philip S. YuGeometric Representation LearningTopological Representation Learning

  6. Efficient Learning of Mechanism Designs and Compositionality

    Oct 29, 2026João Pedro Gandarela, Thiago Rios, Stefan Menzel +1Compositional Representation LearningData-Efficient Learning

  7. ACAM-J-MARS: Multi-Atlas Riemannian Spectral Representations for Decoding Advanced Meditation States from fMRI

    Oct 29, 2026Jian Wang, Winson F. Z. Yang, Wugeng Zheng +1Riemannian Representation LearningNeural Decoding

  8. Geometry-Aware Trajectory State Modeling for Few-Shot Action Recognition

    Oct 28, 2026Zhiqi Miao, Marko Haralović, Stanislav Levendeev +5Few-Shot Action RecognitionVideo Action Recognition

  9. Euclidean Crowding-Driven Adaptive Euclidean-Hyperbolic Graph Learning

    Oct 27, 2026Hao Chen, Jian Sun, Chuan Shi +1Riemannian Representation LearningGraph Representation Learning

  10. Concorde: Geometry-Aware Link Prediction via Decoupled Energy Minimization

    Oct 26, 2026Ege Demirci, Ambuj SinghLink PredictionGraph Embedding

  11. IsoAct: Geometry-Aware Post-hoc Debiasing via Isometric Actions

    Oct 26, 2026Sumin Park, Taero Kim, Minhyeong Cho +3Geometric Representation LearningAlgorithmic Bias

  12. Relational Geometry Forcing for World Action Models

    Oct 21, 2026Yuan Xu, Yixiang Chen, Qisen Ma +10World Models for RoboticsWorld Action Models

  13. Spatially Informed and Direction Sensitive Representation Learning for Spatial Transcriptomics

    Oct 20, 2026Azim Dehghani Amirabad, Ali Khodabandeh Yalabadi, Artem Moskalev +4Representation LearningSpatial Transcriptomics

  14. LocaLeJEPA: Maximum Entropy Representations under Geometric Priors

    Oct 20, 2026Kartik Tandon, Alessio Borgi, Pavel Snopov +8Representation LearningJoint-Embedding Predictive Architecture

  15. From Predictive Geometry to Action: Learning Complementary Predictive Representations for Embodied Manipulation

    Oct 20, 2026Xiaoxu Xu, Hao Li, Hongtao Zhang +6Robotic ManipulationPredictive Representation Learning

  16. Graph Neural Networks for Astrophysics and Cosmology

    Oct 19, 2026Christian Kragh JespersenCosmologyGraph Neural Networks

  17. Inducing Fourier Geometry: A Smoothness Prior Imposes Approximate Translation Equivariance in Multimodal Stellar Embeddings

    Oct 16, 2026Ilay Kamai, Alex M. Bronstein, Hagai B. PeretsGeometric Representation LearningEquivariant Representation Learning

  18. Local Temporal Contrasts on Human Motion Data Induce a Latent Geometry

    Oct 15, 2026Lourenço A. Rodrigues, Felix PutzeTemporal Representation LearningSelf-Supervised Time Series Representation Learning

  19. GeoReader: Learning Latent Geometry for Spatial Reasoning in Vision-Language Models

    Oct 13, 2026Rong Li, Shijie Li, Jiangyong Huang +7Geospatial QAVisual Spatial Reasoning

  20. GeoMER: A Joint Euclidean-Hyperbolic Geometry Framework for Multimodal Emotion Recognition

    Oct 13, 2026Ting Zhu, Huizhi Liang, Boguslaw Obara +2Multimodal Emotion RecognitionMultimodal Fusion

  21. GeoNIRS: Geometry-Aware Pretraining for Heterogeneous fNIRS Representation Learning

    Oct 13, 2026Zongsheng Li, Shengyuan Zhu, Zimo Zhang +3Representation LearningNeuroimaging

  22. VGGA: Geometry-Grounded Autoencoder for Video Generation

    Oct 12, 2026Chaofan Gan, Yian Zhao, Shijie Li +4Video GenerationAutoencoders

  23. The Polytopal Neural Network

    Oct 8, 2026A. Emilie J. Wedenborg, Anders V. Nørskov, Teresa Dorszewski +2Neural Network InterpretabilityGeometric Representation Learning

  24. ΔΔRepresentation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMs

    Oct 7, 2026Hao Wang, Qiwei Zeng, Jinghao Lin +6Medical Image Representation LearningMedical VLMs

  25. Constant-Curvature Sliced Gromov-Wasserstein for Heterogeneous Cross-Curvature Alignment

    Oct 5, 2026Shanglin Li, Wenjing Lu, Muyang Li +2Distribution MatchingGeometric Representation Learning

  26. Less Context, Better Geometry: Masked Geometric Encoder for Robust 3D Foundation Models

    Oct 5, 2026Zhimin Shao, Xijun Liu, Zhaoliang Zhang +43D Foundation ModelsToken Merging

  27. On the Geometry of Multimodal Saturation: Riemannian VICReg

    Oct 5, 2026Nessim Ben Abbes, Duc Han Le, Sabri Mtibaa +1Self-Supervised LearningGeometric Representation Learning

  28. LEAP: Making Privileged Geometry Supervision Effective for Visuomotor Learning

    Oct 4, 2026Han Fang, Yunpeng Jiang, Jianshu Hu +6Visuomotor Policy LearningRobot Imitation Learning