{"total":456,"rows":[{"id":"2104.13478","title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","created":"2021-04-27","cited_by_count":1167,"area":null},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2104.12229","title":"Vector Neurons: A General Framework for SO(3)-Equivariant Networks","created":"2021-04-25","cited_by_count":305,"area":null},{"id":"2101.03288","title":"How to Train Your Energy-Based Models","created":"2021-01-09","cited_by_count":274,"area":null},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264,"area":null},{"id":"2110.02905","title":"Geometric and Physical Quantities Improve E(3) Equivariant Message Passing","created":"2021-10-06","cited_by_count":228,"area":null},{"id":"2306.12059","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","created":"2023-06-21","cited_by_count":204,"area":null},{"id":"2104.09459","title":"A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups","created":"2021-04-19","cited_by_count":187,"area":null},{"id":"2201.12204","title":"From data to functa: Your data point is a function and you can treat it like one","created":"2022-01-28","cited_by_count":187,"area":null},{"id":"2207.09453","title":"e3nn: Euclidean Neural Networks","created":"2022-07-18","cited_by_count":174,"area":null},{"id":"2110.03336","title":"Frame Averaging for Invariant and Equivariant Network Design","created":"2021-10-07","cited_by_count":168,"area":null},{"id":"2101.04562","title":"Hyperbolic Deep Neural Networks: A Survey","created":"2021-01-12","cited_by_count":139,"area":null},{"id":"2303.12766","title":"Spherical Transformer for LiDAR-based 3D Recognition","created":"2023-03-22","cited_by_count":125,"area":null},{"id":"2302.03655","title":"Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs","created":"2023-02-07","cited_by_count":117,"area":null},{"id":"2301.12780","title":"Equivariant Architectures for Learning in Deep Weight Spaces","created":"2023-01-30","cited_by_count":107,"area":null},{"id":"2103.06526","title":"DualPoseNet: Category-level 6D Object Pose and Size Estimation Using Dual Pose Network with Refined Learning of Pose Consistency","created":"2021-03-11","cited_by_count":103,"area":null},{"id":"2203.09283","title":"PanoFormer: Panorama Transformer for Indoor 360 Depth Estimation","created":"2022-03-17","cited_by_count":95,"area":null},{"id":"2209.03954","title":"Learning to Generate Realistic LiDAR Point Clouds","created":"2022-09-08","cited_by_count":93,"area":"wm"},{"id":"2102.10333","title":"Provably Strict Generalisation Benefit for Equivariant Models","created":"2021-02-20","cited_by_count":91,"area":null},{"id":"2102.04776","title":"Generative Models as Distributions of Functions","created":"2021-02-09","cited_by_count":89,"area":null},{"id":"2109.07103","title":"Automatic Symmetry Discovery with Lie Algebra Convolutional Network","created":"2021-09-15","cited_by_count":83,"area":null},{"id":"2103.14147","title":"Equivariant Point Network for 3D Point Cloud Analysis","created":"2021-03-25","cited_by_count":81,"area":null},{"id":"2110.14811","title":"SE(3) Equivariant Graph Neural Networks with Complete Local Frames","created":"2021-10-26","cited_by_count":76,"area":null},{"id":"2211.13609","title":"PAC-Bayes Compression Bounds So Tight That They Can Explain Generalization","created":"2022-11-24","cited_by_count":76,"area":null},{"id":"2104.06954","title":"Aligning Latent and Image Spaces to Connect the Unconnectable","created":"2021-04-14","cited_by_count":70,"area":null},{"id":"2302.14040","title":"Permutation Equivariant Neural Functionals","created":"2023-02-27","cited_by_count":70,"area":null},{"id":"2305.01118","title":"CSP: Self-Supervised Contrastive Spatial Pre-Training for Geospatial-Visual Representations","created":"2023-05-01","cited_by_count":69,"area":null},{"id":"2109.00182","title":"You Only Hypothesize Once: Point Cloud Registration with Rotation-equivariant Descriptors","created":"2021-09-01","cited_by_count":68,"area":null},{"id":"2106.02347","title":"SE(3)-equivariant prediction of molecular wavefunctions and electronic densities","created":"2021-06-04","cited_by_count":67,"area":null},{"id":"2105.13926","title":"Geometric Deep Learning and Equivariant Neural Networks","created":"2021-05-28","cited_by_count":65,"area":null},{"id":"2203.16797","title":"When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning","created":"2022-03-31","cited_by_count":65,"area":null},{"id":"2203.00838","title":"OmniFusion: 360 Monocular Depth Estimation via Geometry-Aware Fusion","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2111.15669","title":"360MonoDepth: High-Resolution 360{\\deg} Monocular Depth Estimation","created":"2021-11-30","cited_by_count":60,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2305.11141","title":"Clifford Group Equivariant Neural Networks","created":"2023-05-18","cited_by_count":55,"area":null},{"id":"2204.11371","title":"Learning Symmetric Embeddings for Equivariant World Models","created":"2022-04-24","cited_by_count":54,"area":"wm"},{"id":"2211.11962","title":"Transformation-Equivariant 3D Object Detection for Autonomous Driving","created":"2022-11-22","cited_by_count":52,"area":null},{"id":"2303.14465","title":"Equivariant Similarity for Vision-Language Foundation Models","created":"2023-03-25","cited_by_count":52,"area":"mllm"},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2207.10758","title":"DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection","created":"2022-07-21","cited_by_count":48,"area":null},{"id":"2110.15255","title":"Self-Supervised Learning Disentangled Group Representation as Feature","created":"2021-10-28","cited_by_count":47,"area":null},{"id":"2206.14331","title":"Spherical Channels for Modeling Atomic Interactions","created":"2022-06-29","cited_by_count":47,"area":null},{"id":"2110.10211","title":"Learning Partial Equivariances from Data","created":"2021-10-19","cited_by_count":45,"area":null},{"id":"2306.05697","title":"Group Equivariant Fourier Neural Operators for Partial Differential Equations","created":"2023-06-09","cited_by_count":45,"area":null},{"id":"2302.10283","title":"Self-supervised learning of Split Invariant Equivariant representations","created":"2023-02-14","cited_by_count":44,"area":null},{"id":"2104.00568","title":"LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering","created":"2021-04-01","cited_by_count":43,"area":null},{"id":"2304.07803","title":"EGformer: Equirectangular Geometry-biased Transformer for 360 Depth Estimation","created":"2023-04-16","cited_by_count":43,"area":null},{"id":"2202.10638","title":"Invariance Learning in Deep Neural Networks with Differentiable Laplace Approximations","created":"2022-02-22","cited_by_count":42,"area":null},{"id":"2302.00236","title":"Generative Adversarial Symmetry Discovery","created":"2023-02-01","cited_by_count":42,"area":null},{"id":"2204.07178","title":"Relaxing Equivariance Constraints with Non-stationary Continuous Filters","created":"2022-04-14","cited_by_count":41,"area":null},{"id":"2108.09432","title":"ARAPReg: An As-Rigid-As Possible Regularization Loss for Learning Deformable Shape Generators","created":"2021-08-21","cited_by_count":40,"area":null},{"id":"2112.14440","title":"ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation","created":"2021-12-29","cited_by_count":39,"area":null},{"id":"2306.17624","title":"Sphere2Vec: A General-Purpose Location Representation Learning over a Spherical Surface for Large-Scale Geospatial Predictions","created":"2023-06-30","cited_by_count":39,"area":null},{"id":"2205.10468","title":"Deep Learning for Omnidirectional Vision: A Survey and New Perspectives","created":"2022-05-21","cited_by_count":38,"area":null},{"id":"2401.11037","title":"Equivariant Graph Neural Operator for Modeling 3D Dynamics","created":"2024-01-19","cited_by_count":38,"area":null},{"id":"2201.12382","title":"Deep Learning Methods for Abstract Visual Reasoning: A Survey on Raven's Progressive Matrices","created":"2022-01-28","cited_by_count":37,"area":"lr"},{"id":"2106.07032","title":"Category Theory in Machine Learning","created":"2021-06-13","cited_by_count":36,"area":null},{"id":"2111.14923","title":"Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models","created":"2021-11-29","cited_by_count":36,"area":null},{"id":"2303.12410","title":"EDGI: Equivariant Diffusion for Planning with Embodied Agents","created":"2023-03-22","cited_by_count":36,"area":"diffusion"},{"id":"2209.02952","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","created":"2022-09-07","cited_by_count":35,"area":null},{"id":"2302.05738","title":"Cross-Modal Fine-Tuning: Align then Refine","created":"2023-02-11","cited_by_count":34,"area":null},{"id":"2112.06536","title":"SphereSR: 360{\\deg} Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation","created":"2021-12-13","cited_by_count":33,"area":null},{"id":"2211.09231","title":"The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry","created":"2022-11-16","cited_by_count":33,"area":null},{"id":"2110.05668","title":"NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse Tasks","created":"2021-10-12","cited_by_count":32,"area":null},{"id":"2402.15332","title":"Position: Categorical Deep Learning is an Algebraic Theory of All Architectures","created":"2024-02-23","cited_by_count":32,"area":null},{"id":"2201.07788","title":"ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes","created":"2022-01-19","cited_by_count":31,"area":null},{"id":"2409.02772","title":"Unifying Causal Representation Learning with the Invariance Principle","created":"2024-09-04","cited_by_count":31,"area":null},{"id":"2101.01000","title":"Conditional Local Convolution for Spatio-temporal Meteorological Forecasting","created":"2021-01-04","cited_by_count":30,"area":null},{"id":"2106.02346","title":"Provably Strict Generalisation Benefit for Invariance in Kernel Methods","created":"2021-06-04","cited_by_count":30,"area":null},{"id":"2310.00105","title":"Latent Space Symmetry Discovery","created":"2023-09-29","cited_by_count":29,"area":null},{"id":"2303.00165","title":"Diffusion Probabilistic Fields","created":"2023-03-01","cited_by_count":28,"area":"diffusion"},{"id":"2303.08942","title":"Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution","created":"2023-03-15","cited_by_count":28,"area":null},{"id":"2106.03375","title":"Commutative Lie Group VAE for Disentanglement Learning","created":"2021-06-07","cited_by_count":27,"area":null},{"id":"2209.13864","title":"USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation","created":"2022-09-28","cited_by_count":27,"area":null},{"id":"2306.06722","title":"$E(2)$-Equivariant Vision Transformer","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2203.09250","title":"Symmetry-Based Representations for Artificial and Biological General Intelligence","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2402.05232","title":"Universal Neural Functionals","created":"2024-02-07","cited_by_count":26,"area":null},{"id":"2103.17001","title":"Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Cameras","created":"2021-03-31","cited_by_count":24,"area":null},{"id":"2202.03990","title":"Equivariance versus Augmentation for Spherical Images","created":"2022-02-08","cited_by_count":24,"area":null},{"id":"2209.13603","title":"Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions","created":"2022-09-27","cited_by_count":24,"area":null},{"id":"2211.15420","title":"Equivariant Networks for Crystal Structures","created":"2022-11-15","cited_by_count":24,"area":null},{"id":"2108.08557","title":"DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders","created":"2021-08-19","cited_by_count":23,"area":null},{"id":"2109.05565","title":"SphereFace Revived: Unifying Hyperspherical Face Recognition","created":"2021-09-12","cited_by_count":23,"area":null},{"id":"2203.06153","title":"Symmetry Group Equivariant Architectures for Physics","created":"2022-03-11","cited_by_count":23,"area":null},{"id":"2207.07065","title":"On the Strong Correlation Between Model Invariance and Generalization","created":"2022-07-14","cited_by_count":23,"area":null},{"id":"2105.05400","title":"Homogeneous vector bundles and $G$-equivariant convolutional neural networks","created":"2021-05-12","cited_by_count":21,"area":null},{"id":"2306.05420","title":"Scaling Spherical CNNs","created":"2023-06-08","cited_by_count":21,"area":null},{"id":"2310.10013","title":"Riemannian Residual Neural Networks","created":"2023-10-16","cited_by_count":21,"area":null},{"id":"2102.06942","title":"Rotation-Equivariant Deep Learning for Diffusion MRI","created":"2021-02-13","cited_by_count":20,"area":null},{"id":"2102.08380","title":"Topological Obstructions to Autoencoding","created":"2021-02-16","cited_by_count":20,"area":null},{"id":"2107.08596","title":"Equivariant Manifold Flows","created":"2021-07-19","cited_by_count":20,"area":null},{"id":"2307.07313","title":"HEAL-SWIN: A Vision Transformer On The Sphere","created":"2023-07-14","cited_by_count":20,"area":null},{"id":"2308.14726","title":"PanoSwin: a Pano-style Swin Transformer for Panorama Understanding","created":"2023-08-28","cited_by_count":20,"area":null},{"id":"2407.09468","title":"Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures","created":"2024-07-12","cited_by_count":20,"area":null},{"id":"2104.03584","title":"PDO-eS2CNNs: Partial Differential Operator Based Equivariant Spherical CNNs","created":"2021-04-08","cited_by_count":19,"area":null},{"id":"2110.06084","title":"Implicit Bias of Linear Equivariant Networks","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2112.01741","title":"Frame Averaging for Equivariant Shape Space Learning","created":"2021-12-03","cited_by_count":19,"area":null},{"id":"2212.08892","title":"Flattening-Net: Deep Regular 2D Representation for 3D Point Cloud Analysis","created":"2022-12-17","cited_by_count":19,"area":null},{"id":"2303.15651","title":"4D Panoptic Segmentation as Invariant and Equivariant Field Prediction","created":"2023-03-28","cited_by_count":19,"area":null},{"id":"2102.02828","title":"Scattering Networks on the Sphere for Scalable and Rotationally Equivariant Spherical CNNs","created":"2021-02-04","cited_by_count":18,"area":null}],"next_cursor":"100"}