Geometric Representation Learning

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 155% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 188

All topics

General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
May 27, 2026Huaihai Lyu, Chaofan Chen, Mingyu Cao +2Geometric Representation Learning Vision-Language-Action Models
1MAIS, Institute of Automation, Chinese Academy of Sciences · 2Beijing Academy of Artificial Intelligence.
SPHERE-JEPA: Spherical Prediction with Homogeneous Embeddings
May 26, 2026L{é}o Nicollier, Max Dunitz, Marc Pic +3Self-Supervised Learning Joint-Embedding Predictive Architecture
CB,ATT · ATT · CB,IFUMI +1
Metric-Aware PCA as a Linear Instance of Geometric Deep Learning
May 25, 2026Michael LeznikPrincipal Component Analysis Geometric Representation Learning
Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
May 23, 2026Yurou Yang, Muyuan Lin, Roberto Martin-Martin +43D Reconstruction Geometric Representation Learning
Amazon Personal Robotics Group · University of Texas at Austin · Massachusetts Institute of Technology
Learning Laplacian Eigenspace with Mass-Aware Neural Operators on Point Clouds
May 23, 2026Zherui Yang, Tao Du, Ligang LiuPoint Cloud Learning Geometric Representation Learning
University of Science and Technology of China, China · Tsinghua University, China · Shanghai Qi Zhi Institute, China +1
GIBLy: Improving 3D Semantic Segmentation through an Architecture-Agnostic Lightweight Geometric Inductive Bias Layer
May 22, 2026Diogo Lavado, Alessandra Micheletti, Clàudia Soares3D Semantic Segmentation Geometric Representation Learning
NOVA School of Science and Technology, Portugal · Universit`a degli Studi di Milano, Italy
VACE: Learning Geometrically Structured Representations for Time Series Anomaly Detection
May 22, 2026Alberto D. Cencillo, Leonardo Concepción, Isaac Triguero +1Self-Supervised Time Series Representation Learning Geometric Representation Learning
1Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) · Department of Computer Science and Artificial Intelligence (DECSAI), University of Granada, Granada, 18071, Spain
Commutator-Induced Uncertainty in VAEs
May 22, 2026Tahereh Dehdarirad, Michael Felsberg, Gabriel Eilertsen +1Variational Autoencoders Disentangled Representation Learning
Computer Vision and Learning Systems (CVL), Linköping University, Sweden · Department of Science and Technology, Linköping University, Sweden
Emergent Semantic Representations in World Models through Physical Interaction without Linguistic Supervision
May 22, 2026Jiayi FangRepresentation Learning World Model Learning
1Shanghai University of Finance and Economics
Uncovering the Latent Potential of Deep Intermediate Representations
May 21, 2026Arnesh Batra, Arush Gumber, Aniket Khandelwal +2Neural Representation Geometry Hierarchical Representation Learning
SBILab, Indraprastha Institute of Information Technology Delhi, Delhi, India.
Disentanglement Beyond Generative Models with Riemannian ICA
May 21, 2026Edmond CunninghamDisentangled Representation Learning Independent Component Analysis
University of Massachusetts Amherst
GA-VLN: Geometry-Aware BEV Representation for Efficient Vision-Language Navigation
May 21, 2026Jiahao Yang, Zihan Wang, Xiangyang Li +4Efficient VLM Inference Geometric Representation Learning
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, Beijing · University of Chinese Academy of Sciences, Beijing · School of Computing, National University of Singapore +2
UniT: Unified Geometry Learning with Group Autoregressive Transformer
May 20, 2026Haotian Wang, Yusong Huang, Zhaonian Kuang +4Transformer Depth Estimation
Intelligent Transportation Thrust of the Systems Hub, The Hong Kong University of Science and Technology (GZ), Guangzhou, P.R.China. · The National Key Laboratory of Human-Machine Hybrid Augmented Intelligence, Xi’an Jiaotong University, Xi’an, P.R.China. · Applied Science, Amazon.com, Inc., USA.
Learning fMRI activations dictionaries across individual geometries via optimal transport
May 20, 2026Sonia Mazelet, Rémi Flamary, Bertrand ThirionLearning to Optimize Geometric Representation Learning
CMAP, Ecole Polytechnique · Palaiseau, France · Mind, Inria-Saclay
GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labels
May 20, 2026Ningkang Peng, Jingyang Mao, Xiaoqian Peng +4Geometric Representation Learning Manifold Learning
Nanjing Normal University Nanjing, China · Nanjing University of Chinese Medicine Nanjing, China
Beyond Isotropy in JEPAs: Hamiltonian Geometry and Symplectic Prediction
May 19, 2026Robert Jenkinson AlvarezJoint-Embedding Predictive Architecture Geometric Representation Learning
GeoMamba: A Geometry-driven MambaVision Framework and Dataset for Fine-grained Optical-SAR Object Retrieval
May 19, 2026Tiantong Fang, Xiuwei Wang, Jing Xiao +3Cross-Modal Representation Learning Geometric Representation Learning
School of Artificial Intelligence, Wuhan University · School of Artificial Intelligence and Information Engineering, Zhejiang University of Science & Technology · Hangzhou Institute of Technology, Xidian University +1
Riemannian Networks over Full-Rank Correlation Matrices
May 18, 2026Ziheng Chen, Xiaojun Wu, Bernhard Schölkopf +1Geometric Representation Learning Manifold Learning
Department of Information Engineering and Computer Science, University of Trento, Trento, Italy · Max Planck Institute for Intelligent Systems, Tübingen, Germany · School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China
Learning to Solve Compositional Geometry Routing Problems
May 18, 2026Mingfeng Fan, Jianan Zhou, Jiaqi Cheng +3Geometric Representation Learning Neural Combinatorial Optimization
National University of Singapore · Nanyang Technological University · Central South University
SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals
May 18, 2026Soyeon Yoon, Chang Wook Seo, Hyunjung ShimGeometric Representation Learning Non-Rigid Shape Correspondence
1KAIST AI · 2Anigma Technologies
Beyond Euclidean Prototypes: Spectral Disentanglement and Geodesic Matching for Few-Shot Medical Image Segmentation
May 18, 2026Penghao Jia, Zhiyong Huang, Mingyang Hou +4Prototype-Based Learning Image Segmentation
School of Microelectronics and Communication Engineering, Chongqing University, Chongqing 400044, China · Health Management Institute, The Second Medical Center, and the National Clinical Research Center for Geriatric Diseases, Chinese PLA General Hospital, Beijing 100853, China · Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China
AURORA: Contextual Orthogonalization for Geometric Representation Learning in Healthcare Foundation Models
May 18, 2026Yuanyun Zhang, Shi LiDisentangled Representation Learning Representation Learning
University of the Chinese Academy of Sciences · Columbia University
GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks
May 15, 2026Davide Buoso, Andrea Protopapa, Stefano Di Carlo +2Vision Foundation Model Adaptation Visuomotor Policy Learning
Department of Control and Computer Engineering, Polytechnic University of Turin, Italy
Neural Point-Forms
May 15, 2026Bruno Trentini, Jacob Hume, Vincenzo Antonio Isoldi +3Point Cloud Learning Geometric Representation Learning
University of Oxford Oxford, UK · School of Engineering and Applied Sciences Harvard University Cambridge, MA, US · Max Planck Institute of Molecular Cell Biology and Genetics Dresden, Germany
Chem-GMNet: A Sphere-Native Geometric Transformer for Molecular Property Prediction
May 13, 2026Deepak Warrier, Raja Sekhar PappalaTransformer Geometric Representation Learning
MSTACK AI
A nonlinear extension of parametric model embedding for dimensionality reduction in parametric shape design
May 12, 2026Andrea Serani, Giorgio Palma, Matteo DiezGeometric Representation Learning Dimensionality Reduction
National Research Council-Institute of Marine Engineering, Rome, Italy
WorldComp2D: Spatio-semantic Representations of Object Identity and Location from Local Views
May 12, 2026SeongMin Jin, Doo Seok JeongRepresentation Learning Visual Representation Learning
1Division of Materials Science and Engineering · Department of Semiconductor Engineering
Steerable Neural ODEs on Homogeneous Spaces
May 11, 2026Emma Andersdotter, Daniel Persson, Fredrik OhlssonEquivariant Neural Networks Geometric Representation Learning
Department of Mathematics and Mathematical Statistics Umeå University Umeå SE-901 87, Sweden · Department of Mathematical Sciences2026 Chalmers University of Technology and Gothenburg University Gothenburg SE-412 96, Sweden · Department of Mathematics and Mathematical Statistics 11 Umeå University Umeå SE-901 87, Sweden
Learning Point Cloud Geometry as a Statistical Manifold: Theory and Practice
May 11, 2026Jinwoo Lee, Jiwoo Kim, Woojae Shin +2Geometric Representation Learning Manifold Learning
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea · Daegu Gyeongbuk Institute of Science and Technology (DGIST), Daegu, Republic of Korea
MARGIN: Margin-Aware Regularized Geometry for Imbalanced Vulnerability Detection
May 11, 2026Yuteng Zhang, Huifang Ma, Jiahui Wei +2Class-Imbalanced Learning Software Vulnerability Detection
College of Artificial Intelligence and Computer Science, Northwest Normal University, Lanzhou 730070, China

May 27, 2026, cs.CVJ/K move · Enter open · S save

General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling

Huaihai Lyu, Chaofan Chen, Mingyu Cao, Yuheng Ji+1

1MAIS, Institute of Automation, Chinese Academy of Sciences · 2Beijing Academy of Artificial Intelligence.

Geometric Representation Learning Vision-Language-Action Models Robot Policy Generalization Invariant Representation Learning

Open paper AskPDF arXiv

Achieving robust generalization from limited data is a central challenge in embodied intelligence. Prevailing methods fail by regressing absolute coordinates, which violates the principle of general covariance. Fundamentally, this conflates the intrinsic task geometry with rigid execution patterns, binding policies to specific motion styles and fixed speeds. To resolve this, we propose the Generalized Action Manifold (GAM) framework that enforces general covariance through structural disentanglement. Specifically, GAM realizes the manifold by enforcing invariance across two orthogonal dimensions: (1) Temporal Invariance, utilizing an Arc-Length Parameterizer to orthogonalize the spatial path geometry from temporal dynamics, ensuring robustness to velocity variations; (2) Geometric Invariance, where a Schema-Affine-Factorization mechanism maps trajectories to canonical ``world lines'' in a pose-normalized coordinate frame. This distinguishes invariant geometric schemas from affine modulations, ensuring spatial generalizability. By integrating GAM within a structured Vision-Language-Action (VLA) architecture, we enable sparse demonstrations to densely populate a continuous, valid action manifold. Empirical results demonstrate that GAM enables superior transfer and robustness capabilities, outperforming geometry-agnostic baselines.

Momentum

Related topics

Latest papers 188