{"total":39,"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":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91,"area":null},{"id":"2108.01513","title":"SphereFace2: Binary Classification is All You Need for Deep Face Recognition","created":"2021-08-03","cited_by_count":42,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2303.05506","title":"TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization","created":"2023-03-09","cited_by_count":32,"area":null},{"id":"2203.05483","title":"projUNN: efficient method for training deep networks with unitary matrices","created":"2022-03-10","cited_by_count":27,"area":null},{"id":"2102.07227","title":"Learning by Turning: Neural Architecture Aware Optimisation","created":"2021-02-14","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":"2404.04316","title":"Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation","created":"2024-04-05","cited_by_count":21,"area":null},{"id":"2206.00845","title":"Hyperspherical Consistency Regularization","created":"2022-06-02","cited_by_count":16,"area":null},{"id":"2110.14098","title":"Provable Lifelong Learning of Representations","created":"2021-10-27","cited_by_count":15,"area":null},{"id":"2303.06484","title":"Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap","created":"2023-03-11","cited_by_count":14,"area":null},{"id":"2210.05398","title":"Continual Learning by Modeling Intra-Class Variation","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2409.00119","title":"3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2506.08001","title":"Reparameterized LLM Training via Orthogonal Equivalence Transformation","created":"2025-06-09","cited_by_count":9,"area":null},{"id":"2210.17467","title":"Iterative Teaching by Data Hallucination","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2503.15355","title":"Robustness of Nonlinear Representation Learning","created":"2025-03-19","cited_by_count":7,"area":null},{"id":"2410.13618","title":"LoLDU: Low-Rank Adaptation via Lower-Diag-Upper Decomposition for Parameter-Efficient Fine-Tuning","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2605.12492","title":"Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation","created":"2026-05-12","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":"2305.15912","title":"Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks","created":"2023-05-25","cited_by_count":5,"area":null},{"id":"2603.05500","title":"POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation","created":"2026-03-05","cited_by_count":5,"area":null},{"id":"2206.15204","title":"Data-Efficient Learning via Minimizing Hyperspherical Energy","created":"2022-06-30","cited_by_count":4,"area":null},{"id":"2212.12653","title":"Hyperspherical Quantization: Toward Smaller and More Accurate Models","created":"2022-12-24","cited_by_count":4,"area":null},{"id":"2310.09449","title":"Pairwise Similarity Learning is SimPLE","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2505.11235","title":"Efficient Orthogonal Fine-Tuning with Principal Subspace Adaptation","created":"2025-05-16","cited_by_count":4,"area":null},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2605.28819","title":"PEFT-Arena: Understanding Parameter-Efficient Finetuning from a Stability-Plasticity Perspective","created":"2026-05-27","cited_by_count":3,"area":null},{"id":"2305.19294","title":"Investigating the Effects of Fairness Interventions Using Pointwise Representational Similarity","created":"2023-05-30","cited_by_count":2,"area":null},{"id":"2506.02453","title":"PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation","created":"2025-06-03","cited_by_count":2,"area":null},{"id":"2504.00885","title":"Spectral Architecture Search for Neural Network Models","created":"2025-04-01","cited_by_count":1,"area":null},{"id":"2506.19022","title":"Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2207.05532","title":"Utilizing Excess Resources in Training Neural Networks","created":"2022-07-12","cited_by_count":0,"area":null},{"id":"2309.17215","title":"Sharpness-Aware Teleportation on Riemannian Manifolds","created":"2023-09-29","cited_by_count":0,"area":null},{"id":"2502.06268","title":"Spectral-factorized Positive-definite Curvature Learning for NN Training","created":"2025-02-10","cited_by_count":0,"area":null},{"id":"2507.04310","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2605.11872","title":"LOFT: Low-Rank Orthogonal Fine-Tuning via Task-Aware Support Selection","created":"2026-05-12","cited_by_count":0,"area":null}],"next_cursor":null}