Equivariant Neural Networks

Follow this topic Ask about this topic

Latest papers 146

18 papers in the last four weeks, up 38% on the four weeks before. 0.1% of all new papers.

All topics

A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$
Jun 26, 2026Tīkun Ông, Georg BökmanVision Transformer Equivariant Neural Networks
Independent Researcher · University of Amsterdam
Equivariance and Augmentation for Bayesian Neural Networks
Jun 24, 2026Miaowen Dong, Axel Flinth, Jan E. GerkenBayesian Neural Networks Data Augmentation
Department of Mathematical Sciences, Chalmers University of Technology and the University of Gothenburg, SE-412 96 Gothenburg, Sweden. · Department of Mathematics and Mathematical Statistics, Umeå University, Linnéus väg 49, 901 87 Umeå, Sweden.
REViT: Roto-reflection Equivariant Convolutional Vision Transformer
Jun 24, 2026Sheir A. Zaheer, Alexander C. Holston, Chan Y. ParkVision Transformer Equivariant Neural Networks
1KC Machine Learning Lab, Seoul, Rep. of Korea.
Scalable Peptide Design via Memory-Efficient Equivariant Transformer
Jun 23, 2026Rui Jiao, Xiangzhe Kong, Yinjun Jia +4Equivariant Neural Networks Efficient Attention
Department of Computer Science and Technology, Tsinghua University · Institute for AI Industry Research, Tsinghua University · Department of Electronic Engineering, Tsinghua University +1
Conformal Orbit-Valid Trust Horizons for Equivariant World Models
Jun 23, 2026Hongbo WangEquivariant Neural Networks Conformal Prediction
Department of Mathematics, Stony Brook University, Stony Brook, NY 11794, USA
MeshFlow: Mesh Generation with Equivariant Flow Matching
Jun 22, 2026Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan +6Flow Matching 3D Mesh Generation
City University of Hong Kong, Hong Kong · Stanford University, USA · Cornell Tech, USA +1
What Do Lorentz-Equivariant Jet Taggers Learn?
Jun 19, 2026Jay Agarwal, Siddharth Khare, Dhruv KumarJet Tagging Equivariant Neural Networks
BITS Pilani, Pilani, India.
SWAP: Symmetric Equivariant World-Model for Agile Robot Parkour
Jun 18, 2026Kaixin Lan, Ze Wang, Hongyi Li +6World Models for Robotics Equivariant Neural Networks
Center for X-Mechanics, Zhejiang University, Hangzhou, China · Mirrorme Technology Co., Ltd. Shanghai, China · ZJU-Hangzhou Global Scientific and Technology Innovation Center, Hangzhou, China
Robust and Interpretable Adaptation of Equivariant Materials Foundation Models via Sparsity-promoting Fine-tuning
Jun 17, 2026Youngwoo Cho, Seunghoon Yi, Wooil Yang +6Machine Learning Interatomic Potentials Equivariant Neural Networks
KAIST · Seoul National Univ. · KIAS +2
Privacy from Symmetry: Orthogonally Equivariant Transformers for LLM Inference
Jun 15, 2026Alexander Yukhimchuk, Andrey Shulga, Mladen Kolar +1Privacy-Preserving Language Models LLM Inference
MBZUAI · University of Southern California
Bayesian 3D Steerable CNNs: Enabling Equivariance and Uncertainty Quantification Simultaneously
Jun 13, 2026Abhishek Keripale, Ponkrshnan Thiagarajan, Susanta GhoshBayesian Neural Networks Uncertainty Quantification
Department of Mechanical and Aerospace Engineering, Michigan Technological University, Houghton, MI 49931 · Hopkins Extreme Materials Institute, Johns Hopkins University, Baltimore, MD 21218 · The Center for Artificial Intelligence at the Institute of Computing and Cybersystems, Michigan Technological University, USA
Dual-Domain Equivariant Generative Adversarial Network for Multimodal CT-PET Synthesis
Jun 11, 2026Gabriel Steele, Alzahra Altalib, Alessandro PerelliEquivariant Neural Networks PET/CT Imaging
School of Science and Engineering, University of Dundee, DD1 4HN, UK · Faculty of Applied Medical Sciences, Jordan University of Science and Technology, 21410, Jordan · School of Cardiovascular and Metabolic Health, University of Glasgow, G12 8TA, UK
Certified World Models: Predictability Across Configuration, Horizon, and Resolution
Jun 11, 2026Hongbo WangEquivariant Neural Networks Latent World Models
Department of Mathematics, Stony Brook University, Stony Brook, NY 11794, USA
EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows
Jun 10, 2026Clinton Enwerem, John S. Baras, Calin BeltaRobotic Grasping Contact-Rich Robotic Manipulation
Institute for Systems Research, University of Maryland, College Park, MD, U.S.A.
Magnetic HIP-NN for spin dynamics in disordered itinerant magnets
Jun 9, 2026Supriyo Ghosh, Yunhao Fan, Sheng Zhang +2Equivariant Neural Networks Message Passing Neural Networks
Department of Physics, University of Virginia, Charlottesville, Virginia 22904, USA · Department of Chemistry, University of Chicago, Chicago, IL 60637, USA · Theoretical Division and CNLS, Los Alamos National Laboratory, Los Alamos, New Mexico 87545, USA
Equivariant Neural Belief Propagation
Jun 4, 2026Zehua Cheng, Wei Dai, Jiahao SunFactor Graph Optimization Gaussian Mixture Models
Department of Computer Science, University of Oxford, Oxford, United Kingdom · FLock.io, London, United Kingdom
Exact equivariance, kept through training, buys zero-shot generalisation across the symmetry group
Jun 2, 2026Hongbo WangWorld Models for Robotics World Models
Department of Mathematics, Stony Brook University, Stony Brook, NY 11794, USA
Theoretical Aspects of Lie Groupoid and Lie Algebroid Equivariant Convolutional Neural Networks
Jun 1, 2026Michael AstwoodEquivariant Neural Networks Convolutional Neural Networks
Department of Mathematics, University of Manitoba, Winnipeg, MB, R3T 2M6 Canada
Revisiting Neural Processes via Fourier Transform and Volterra Series
May 31, 2026Peiman Mohseni, Nick Duffield, Raymond K. W. WongNeural Processes Frequency-Domain Feature Learning
Texas A&M University, College Station, Texas, USA.
Measuring the Symmetry--Data Exchange Rate
May 31, 2026Ahmed M. AdlySample Complexity Equivariant Neural Networks
Independent Researcher · Egypt
MViewRouter: Internalizing Geometric Equivariance via Multi-view Alternating Attention for Combinatorial Routing
May 31, 2026Shiyan Liu, Bohan Tan, Yaoxin Wu +1Traveling Salesperson Problem Multi-View Learning
Huazhong University of Science and Technology · Eindhoven University of Technology
Eyes All Around: Design and Analysis of 360-Degree LiDAR Perception Using Equivariant Feature Learning in Unstructured Traffic
May 30, 2026Pranav Darshan, Raghuveer Narayanan Rajesh, M Uttara KumariLidar-Based 3D Object Detection Point Cloud Learning
Department of Computer Science and Engineering RV College of Engineering, Bengaluru 560059, India · Department of Electronics and Communication Engineering RV College of Engineering, Bengaluru 560059, India
Limits of Resolution Equivariance in Fourier Neural Operators
May 30, 2026Alex Colagrande, Paul Caillon, Eva Feillet +1Fourier Neural Operator Equivariant Neural Networks
Miles Team, LAMSADE, Universit´e Paris Dauphine-PSL, Paris, France · Universit´e Paris-Saclay, CNRS, LISN, France · ESPCI PSL, Paris, France
Equivariant Latent Alignment via Flow Matching under Group Symmetries
May 29, 2026Sunghyun Kim, Jaehoon Hahm, Jeongwoo Shin +1Flow Matching Equivariant Neural Networks
1Seoul National University, Seoul, Korea · University of Illinois Urbana-Champaign, Illinois, USA
On the Equivariant Learning of the $Q$ -tensor Order Parameter
May 26, 2026Julia Navarro, Mark WilkinsonEquivariant Neural Networks Materials Science
Nottingham Trent University, UK · Berea College, USA
How the Optimizer Shapes Learned Solutions in Equivariant Neural Networks
May 26, 2026Teodor-Mihai Stupariu, Andrei ManolacheNeural Representation Geometry Neural Network Optimization
1Bitdefender, Romania · 2Tudor Vianu High School of Com · University of Stuttgart, Germany +1
Planning Neural Dynamics with Lie Group Embedding through Supervised Projective Manifold Learning
May 24, 2026Tianwei Wang, Bryan Chen, Qian Zuo +3Dynamic Neural Networks Equivariant Neural Networks
School of Informatics University of Edinburgh · Bio-inspired Computing and Machine Learning (BCML) Lab · School of Mathematics University of Edinburgh +2
Velocityformer: Broken-Symmetry-Matched Equivariant Graph Transformers for Cosmological Velocity Reconstruction
May 20, 2026Tilman Tröster, David Mirkovic, Veronika Oehl +1Equivariant Neural Networks Equivariant GNNs
Department of Physics ETH Zürich
Exact Symmetry as Algebra: Group-Structured Tensors that Enforce Physical Selection Rules
May 19, 2026Paulina Hoyos, Shashanka Ubaru, Dongsung Huh +5Scientific Discovery Equivariant Neural Networks
UT Austin · IBM Research · Independent +2
Scale-Equivariant Generative Forecasting: Weight-Tied Dilated Convolutions, Wavelet Scattering Inputs, and Spectral-Consistency Training for Self-Similar Time Series
May 17, 2026Andrea MorandiTime Series Forecasting Equivariant Neural Networks
Cisco Systems, Inc.

Jun 26, 2026J/K move · Enter open · S save

A Unified Framework for Vision Transformers Equivariant to Discrete Subgroups of $\mathrm{O}(2)$

Tīkun Ông, Georg Bökman

Independent Researcher · University of Amsterdam

Vision Transformer Equivariant Neural Networks Equivariant Representation Learning Image Classification

Open paper AskPDF arXiv

Vision transformers have become a dominant architecture for visual recognition. However, standard models do not explicitly encode the planar symmetries that arise in many vision domains. We introduce a family of vision transformers equivariant to arbitrary discrete subgroups of

\mathrm{O}(2)

, providing a unified framework that generalizes prior flipping- and

D_4

-equivariant transformer architectures. Our construction yields equivariant analogues of the core transformer components, together with expressivity guarantees for the resulting layers. In particular, we show that whenever

H \le G

, the class of

G

-equivariant ViTs embeds naturally into the class of

H

-equivariant ViTs. We also prove that, in the single-head setting, the corresponding equivariant self-attention layer realizes every

G

-equivariant self-attention map representable by ordinary self-attention. We further construct a

D_6

-equivariant model based on hexagonal patches, making the architecture compatible with six-fold rotational symmetries. We evaluate the resulting models on the PatternNet aerial image dataset in artificially data-scarce regimes across subgroups of

D_4

and

D_6

. Our experiments compare two equivariant attention mechanisms and analyze how the choice of homogeneous-space configurations used in the nonlinearities affects performance. Preliminary results under matched parameter budgets indicate that equivariance can improve recognition accuracy, motivating further study of how discrete symmetry groups shape transformer-based visual recognition models.