{"total":92,"rows":[{"id":"2106.14448","title":"R-Drop: Regularized Dropout for Neural Networks","created":"2021-06-28","cited_by_count":202,"area":null},{"id":"2202.08345","title":"Learning Smooth Neural Functions via Lipschitz Regularization","created":"2022-02-16","cited_by_count":86,"area":null},{"id":"2311.11385","title":"Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts","created":"2023-11-19","cited_by_count":49,"area":null},{"id":"2406.01775","title":"OLoRA: Orthonormal Low-Rank Adaptation of Large Language Models","created":"2024-06-03","cited_by_count":39,"area":null},{"id":"2506.13018","title":"Symmetry in Neural Network Parameter Spaces","created":"2025-06-16","cited_by_count":36,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2203.06345","title":"The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy","created":"2022-03-12","cited_by_count":35,"area":null},{"id":"2102.07091","title":"Decentralized Riemannian Gradient Descent on the Stiefel Manifold","created":"2021-02-14","cited_by_count":33,"area":null},{"id":"2106.05275","title":"Tractable Density Estimation on Learned Manifolds with Conformal Embedding Flows","created":"2021-06-09","cited_by_count":31,"area":null},{"id":"2104.05097","title":"Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networks","created":"2021-04-11","cited_by_count":30,"area":null},{"id":"2302.08210","title":"A Survey of Geometric Optimization for Deep Learning: From Euclidean Space to Riemannian Manifold","created":"2023-02-16","cited_by_count":21,"area":null},{"id":"2105.04854","title":"Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity","created":"2021-05-11","cited_by_count":20,"area":null},{"id":"2112.03328","title":"Learning Connectivity with Graph Convolutional Networks for Skeleton-based Action Recognition","created":"2021-12-06","cited_by_count":20,"area":null},{"id":"2109.11338","title":"Orthogonal Graph Neural Networks","created":"2021-09-23","cited_by_count":19,"area":null},{"id":"2108.05623","title":"Existence, Stability and Scalability of Orthogonal Convolutional Neural Networks","created":"2021-08-12","cited_by_count":16,"area":null},{"id":"2207.12534","title":"Trainability Preserving Neural Pruning","created":"2022-07-25","cited_by_count":16,"area":null},{"id":"2402.06244","title":"Quantifying and Enhancing Multi-modal Robustness with Modality Preference","created":"2024-02-09","cited_by_count":16,"area":null},{"id":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2204.06233","title":"Approximation of Lipschitz Functions using Deep Spline Neural Networks","created":"2022-04-13","cited_by_count":15,"area":null},{"id":"2204.11418","title":"Riemannian Hamiltonian methods for min-max optimization on manifolds","created":"2022-04-25","cited_by_count":12,"area":null},{"id":"2601.23000","title":"Mano: Restriking Manifold Optimization for LLM Training","created":"2026-01-30","cited_by_count":12,"area":null},{"id":"2112.14949","title":"Decentralized Optimization Over the Stiefel Manifold by an Approximate Augmented Lagrangian Function","created":"2021-12-30","cited_by_count":11,"area":null},{"id":"2401.10341","title":"ELRT: Efficient Low-Rank Training for Compact Convolutional Neural Networks","created":"2024-01-18","cited_by_count":11,"area":null},{"id":"2206.02041","title":"First-Order Algorithms for Min-Max Optimization in Geodesic Metric Spaces","created":"2022-06-04","cited_by_count":10,"area":null},{"id":"2508.17901","title":"Riemannian Optimization for LoRA on the Stiefel Manifold","created":"2025-08-25","cited_by_count":10,"area":null},{"id":"2310.10563","title":"RefConv: Re-parameterized Refocusing Convolution for Powerful ConvNets","created":"2023-10-16","cited_by_count":9,"area":null},{"id":"2411.00392","title":"Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization","created":"2024-11-01","cited_by_count":9,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2509.16664","title":"$\\boldsymbol{\\lambda}$-Orthogonality Regularization for Compatible Representation Learning","created":"2025-09-20","cited_by_count":8,"area":null},{"id":"2601.21487","title":"Manifold constrained steepest descent for smooth and closed-set optimization","created":"2026-01-29","cited_by_count":8,"area":null},{"id":"2105.09109","title":"An Orthogonal Classifier for Improving the Adversarial Robustness of Neural Networks","created":"2021-05-19","cited_by_count":7,"area":null},{"id":"2302.03825","title":"Decentralized Riemannian Algorithm for Nonconvex Minimax Problems","created":"2023-02-08","cited_by_count":7,"area":null},{"id":"2308.10547","title":"Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold","created":"2023-08-21","cited_by_count":7,"area":null},{"id":"2306.06365","title":"FalconNet: Factorization for the Light-weight ConvNets","created":"2023-06-10","cited_by_count":6,"area":null},{"id":"2405.20980","title":"Neural Gaussian Scale-Space Fields","created":"2024-05-31","cited_by_count":6,"area":null},{"id":"2108.00051","title":"Coordinate descent on the orthogonal group for recurrent neural network training","created":"2021-07-30","cited_by_count":5,"area":null},{"id":"2205.08385","title":"Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs","created":"2022-05-12","cited_by_count":5,"area":null},{"id":"2310.03696","title":"Function-Space Optimality of Neural Architectures with Multivariate Nonlinearities","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2403.13351","title":"OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2409.00055","title":"SORSA: Singular Values and Orthonormal Regularized Singular Vectors Adaptation of Large Language Models","created":"2024-08-21","cited_by_count":5,"area":null},{"id":"2512.17090","title":"How to Square Tensor Networks and Circuits Without Squaring Them","created":"2025-12-18","cited_by_count":5,"area":null},{"id":"2101.02916","title":"Accelerating Training of Batch Normalization: A Manifold Perspective","created":"2021-01-08","cited_by_count":4,"area":null},{"id":"2106.10704","title":"Better Training using Weight-Constrained Stochastic Dynamics","created":"2021-06-20","cited_by_count":4,"area":null},{"id":"2206.01261","title":"Entangled Residual Mappings","created":"2022-06-02","cited_by_count":4,"area":null},{"id":"2406.19301","title":"MCNC: Manifold-Constrained Reparameterization for Neural Compression","created":"2024-06-27","cited_by_count":4,"area":null},{"id":"2601.03889","title":"Spectral Manifold Regularization for Stable and Modular Routing in Deep MoE Architectures","created":"2026-01-07","cited_by_count":4,"area":"moe"},{"id":"2101.02944","title":"BN-invariant sharpness regularizes the training model to better generalization","created":"2021-01-08","cited_by_count":3,"area":null},{"id":"2103.06583","title":"Preprint: Norm Loss: An efficient yet effective regularization method for deep neural networks","created":"2021-03-11","cited_by_count":3,"area":null},{"id":"2110.09374","title":"Ortho-Shot: Low Displacement Rank Regularization with Data Augmentation for Few-Shot Learning","created":"2021-10-18","cited_by_count":3,"area":null},{"id":"2302.11446","title":"Singular value decomposition based matrix surgery","created":"2023-02-22","cited_by_count":3,"area":null},{"id":"2306.09939","title":"Towards Better Orthogonality Regularization with Disentangled Norm in Training Deep CNNs","created":"2023-06-16","cited_by_count":3,"area":null},{"id":"2102.11855","title":"Deep Unitary Convolutional Neural Networks","created":"2021-02-23","cited_by_count":2,"area":null},{"id":"2103.16634","title":"Exploiting Invariance in Training Deep Neural Networks","created":"2021-03-30","cited_by_count":2,"area":null},{"id":"2105.08911","title":"Multi-layer Perceptron Trainability Explained via Variability","created":"2021-05-19","cited_by_count":2,"area":null},{"id":"2208.13643","title":"A Variance-Reduced Stochastic Gradient Tracking Algorithm for Decentralized Optimization with Orthogonality Constraints","created":"2022-08-29","cited_by_count":2,"area":null},{"id":"2306.10001","title":"Group Orthogonalization Regularization For Vision Models Adaptation and Robustness","created":"2023-06-16","cited_by_count":2,"area":null},{"id":"2306.16617","title":"Last-Iterate Convergence of Adaptive Riemannian Gradient Descent for Equilibrium Computation","created":"2023-06-29","cited_by_count":2,"area":null},{"id":"2406.04249","title":"Conv-INR: Convolutional Implicit Neural Representation for Multimodal Visual Signals","created":"2024-06-06","cited_by_count":2,"area":null},{"id":"2408.07072","title":"Bounds on the geodesic distances on the Stiefel manifold for a family of Riemannian metrics","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2412.07883","title":"On Faster Marginalization with Squared Circuits via Orthonormalization","created":"2024-12-10","cited_by_count":2,"area":null},{"id":"2512.22447","title":"Towards Robust Optical-SAR Object Detection under Missing Modalities: A Dynamic Quality-Aware Fusion Framework","created":"2025-12-27","cited_by_count":2,"area":null},{"id":"2103.11590","title":"Delving into Variance Transmission and Normalization: Shift of Average Gradient Makes the Network Collapse","created":"2021-03-22","cited_by_count":1,"area":null},{"id":"2104.04255","title":"Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks","created":"2021-04-09","cited_by_count":1,"area":null},{"id":"2106.00003","title":"Parallelized Computation and Backpropagation Under Angle-Parametrized Orthogonal Matrices","created":"2021-05-30","cited_by_count":1,"area":null},{"id":"2302.04088","title":"FFHR: Fully and Flexible Hyperbolic Representation for Knowledge Graph Completion","created":"2023-02-07","cited_by_count":1,"area":null},{"id":"2311.14658","title":"Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks","created":"2023-11-24","cited_by_count":1,"area":null},{"id":"2410.03977","title":"Learning to Balance: Diverse Normalization for Cloth-Changing Person Re-Identification","created":"2024-10-04","cited_by_count":1,"area":null},{"id":"2501.15235","title":"Large-Scale Riemannian Meta-Optimization via Subspace Adaptation","created":"2025-01-25","cited_by_count":1,"area":null},{"id":"2506.00798","title":"A Dynamic Stiefel Graph Neural Network for Efficient Spatio-Temporal Time Series Forecasting","created":"2025-06-01","cited_by_count":1,"area":null},{"id":"2506.07351","title":"Decentralized Optimization on Compact Submanifolds by Quantized Riemannian Gradient Tracking","created":"2025-06-09","cited_by_count":1,"area":null},{"id":"2602.19530","title":"ORION: ORthonormal Text Encoding for Universal VLM AdaptatION","created":"2026-02-23","cited_by_count":1,"area":"mllm"},{"id":"2603.03238","title":"On Geometry Regularization in Autoencoder Reduced-Order Models with Latent Neural ODE Dynamics","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.08374","title":"This Looks Distinctly Like That: Grounding Interpretable Recognition in Stiefel Geometry against Neural Collapse","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2606.13276","title":"Different Layers, Different Manifolds: Module-Wise Weight-Space Geometry in Transformer Optimization","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2102.10052","title":"A Projection Algorithm for the Unitary Weights","created":"2021-02-19","cited_by_count":0,"area":null},{"id":"2106.04088","title":"A Lightweight and Gradient-Stable Neural Layer","created":"2021-06-08","cited_by_count":0,"area":null},{"id":"2208.00921","title":"AdaWCT: Adaptive Whitening and Coloring Style Injection","created":"2022-08-01","cited_by_count":0,"area":null},{"id":"2210.06546","title":"Auto-Encoding Goodness of Fit","created":"2022-10-12","cited_by_count":0,"area":null},{"id":"2211.13902","title":"TAOTF: A Two-stage Approximately Orthogonal Training Framework in Deep Neural Networks","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2404.07083","title":"Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting","created":"2024-04-10","cited_by_count":0,"area":null},{"id":"2405.17458","title":"Blood Glucose Control Via Pre-trained Counterfactual Invertible Neural Networks","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2407.08214","title":"Towards stable training of parallel continual learning","created":"2024-07-11","cited_by_count":0,"area":null},{"id":"2407.08374","title":"Enhancing Robustness of Vision-Language Models through Orthogonality Learning and Self-Regularization","created":"2024-07-11","cited_by_count":0,"area":"mllm"},{"id":"2407.21359","title":"ProSpec RL: Plan Ahead, then Execute","created":"2024-07-31","cited_by_count":0,"area":null},{"id":"2507.22045","title":"Weight-Parameterization in Continuous Time Deep Neural Networks for Surrogate Modeling","created":"2025-07-29","cited_by_count":0,"area":null},{"id":"2601.07632","title":"GeoMotionGPT: Geometry-Aligned Motion Understanding with Large Language Models","created":"2026-01-12","cited_by_count":0,"area":null},{"id":"2601.23131","title":"Regularisation in neural networks: a survey and empirical analysis of approaches","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.12613","title":"Coden: Efficient Temporal Graph Neural Networks for Continuous Prediction","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2605.20302","title":"Neural Collapse by Design: Learning Class Prototypes on the Hypersphere","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.28573","title":"Efficient Pre-Training of LLMs through Truncated SVD Representations","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.04535","title":"ManifoldFlow: Spectrum-Learnable Stiefel Optimization via SPD Relaxation","created":"2026-07-05","cited_by_count":0,"area":null},{"id":"2609.19363","title":"Directions That Don't Drift: Stiefel Manifold Routing for Transformer Attention","created":"2026-09-16","cited_by_count":0,"area":null}],"next_cursor":null}