{"total":35,"rows":[{"id":"2105.02375","title":"A Geometric Analysis of Neural Collapse with Unconstrained Features","created":"2021-05-06","cited_by_count":227,"area":null},{"id":"2210.06313","title":"The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers","created":"2022-10-12","cited_by_count":122,"area":null},{"id":"2104.07167","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","created":"2021-04-14","cited_by_count":105,"area":null},{"id":"2107.02392","title":"Dirichlet Energy Constrained Learning for Deep Graph Neural Networks","created":"2021-07-06","cited_by_count":97,"area":null},{"id":"2203.01238","title":"On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features","created":"2022-03-02","cited_by_count":97,"area":null},{"id":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"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":"2203.08120","title":"Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers","created":"2022-03-15","cited_by_count":28,"area":null},{"id":"2106.05956","title":"Beyond BatchNorm: Towards a Unified Understanding of Normalization in Deep Learning","created":"2021-06-10","cited_by_count":25,"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":"2103.00673","title":"Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training","created":"2021-03-01","cited_by_count":15,"area":null},{"id":"2210.12945","title":"Revisiting Sparse Convolutional Model for Visual Recognition","created":"2022-10-24","cited_by_count":14,"area":null},{"id":"2303.09261","title":"Orthogonal Directions Constrained Gradient Method: from non-linear equality constraints to Stiefel manifold","created":"2023-03-16","cited_by_count":14,"area":null},{"id":"2210.08122","title":"Old can be Gold: Better Gradient Flow can Make Vanilla-GCNs Great Again","created":"2022-10-14","cited_by_count":11,"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":"2501.07930","title":"An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures","created":"2025-01-14","cited_by_count":8,"area":null},{"id":"2106.09121","title":"Scaling-up Diverse Orthogonal Convolutional Networks with a Paraunitary Framework","created":"2021-06-16","cited_by_count":7,"area":null},{"id":"2503.15355","title":"Robustness of Nonlinear Representation Learning","created":"2025-03-19","cited_by_count":7,"area":null},{"id":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6,"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":"2212.05599","title":"Orthogonal SVD Covariance Conditioning and Latent Disentanglement","created":"2022-12-11","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":"2503.04626","title":"IDInit: A Universal and Stable Initialization Method for Neural Network Training","created":"2025-03-06","cited_by_count":5,"area":null},{"id":"2505.15174","title":"Enhancing Certified Robustness via Block Reflector Orthogonal Layers and Logit Annealing Loss","created":"2025-05-21","cited_by_count":5,"area":null},{"id":"2207.02119","title":"Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality","created":"2022-07-05","cited_by_count":4,"area":null},{"id":"2311.18296","title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","created":"2023-11-30","cited_by_count":4,"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":"2308.01547","title":"Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation","created":"2023-08-03","cited_by_count":3,"area":null},{"id":"2106.09756","title":"PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python","created":"2021-06-17","cited_by_count":2,"area":null},{"id":"2205.10089","title":"Kernel Normalized Convolutional Networks","created":"2022-05-20","cited_by_count":2,"area":null},{"id":"2302.10383","title":"On Interpretable Approaches to Cluster, Classify and Represent Multi-Subspace Data via Minimum Lossy Coding Length based on Rate-Distortion Theory","created":"2023-02-21","cited_by_count":0,"area":null},{"id":"2310.14206","title":"Manifold-Preserving Transformers are Effective for Short-Long Range Encoding","created":"2023-10-22","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":"2601.13776","title":"Orthogonium : A Unified, Efficient Library of Orthogonal and 1-Lipschitz Building Blocks","created":"2026-01-20","cited_by_count":0,"area":null}],"next_cursor":null}