{"total":39,"rows":[{"id":"2205.10268","title":"B-cos Networks: Alignment is All We Need for Interpretability","created":"2022-05-20","cited_by_count":88,"area":null},{"id":"2410.01131","title":"nGPT: Normalized Transformer with Representation Learning on the Hypersphere","created":"2024-10-01","cited_by_count":70,"area":null},{"id":"2103.01649","title":"Learning with Hyperspherical Uniformity","created":"2021-03-02","cited_by_count":35,"area":null},{"id":"2306.10898","title":"B-cos Alignment for Inherently Interpretable CNNs and Vision Transformers","created":"2023-06-19","cited_by_count":31,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"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":"2206.08704","title":"Maximum Class Separation as Inductive Bias in One Matrix","created":"2022-06-17","cited_by_count":21,"area":null},{"id":"2110.14577","title":"A Geometric Perspective towards Neural Calibration via Sensitivity Decomposition","created":"2021-10-27","cited_by_count":19,"area":null},{"id":"2606.16899","title":"Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization","created":"2026-06-15","cited_by_count":16,"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":"2512.10938","title":"Stronger Normalization-Free Transformers","created":"2025-12-11","cited_by_count":13,"area":null},{"id":"2210.05398","title":"Continual Learning by Modeling Intra-Class Variation","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"area":null},{"id":"2402.18372","title":"FedUV: Uniformity and Variance for Heterogeneous Federated Learning","created":"2024-02-27","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":"2210.17467","title":"Iterative Teaching by Data Hallucination","created":"2022-10-31","cited_by_count":8,"area":null},{"id":"2110.15231","title":"Exploring Covariate and Concept Shift for Detection and Calibration of Out-of-Distribution Data","created":"2021-10-28","cited_by_count":7,"area":null},{"id":"2301.06116","title":"Maximally Compact and Separated Features with Regular Polytope Networks","created":"2023-01-15","cited_by_count":5,"area":null},{"id":"2309.04081","title":"UER: A Heuristic Bias Addressing Approach for Online Continual Learning","created":"2023-09-08","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":"2510.21223","title":"Model Merging with Functional Dual Anchors","created":"2025-10-24","cited_by_count":4,"area":null},{"id":"2602.05943","title":"Orthogonal Model Merging","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2403.16937","title":"Hyperspherical Classification with Dynamic Label-to-Prototype Assignment","created":"2024-03-25","cited_by_count":3,"area":null},{"id":"2506.15617","title":"The Compositional Architecture of Regret in Large Language Models","created":"2025-06-18","cited_by_count":3,"area":null},{"id":"2112.05827","title":"Quality-Aware Multimodal Biometric Recognition","created":"2021-12-10","cited_by_count":2,"area":null},{"id":"2305.10293","title":"Infinite Class Mixup","created":"2023-05-17","cited_by_count":2,"area":null},{"id":"2307.05901","title":"Single Domain Generalization via Normalised Cross-correlation Based Convolutions","created":"2023-07-12","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":"2206.07918","title":"\"Understanding Robustness Lottery\": A Geometric Visual Comparative Analysis of Neural Network Pruning Approaches","created":"2022-06-16","cited_by_count":1,"area":null},{"id":"2405.07171","title":"Enhanced Online Test-time Adaptation with Feature-Weight Cosine Alignment","created":"2024-05-12","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":"2605.04418","title":"Demystifying Manifold Constraints in LLM Pre-training","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2207.02625","title":"$L_2$BN: Enhancing Batch Normalization by Equalizing the $L_2$ Norms of Features","created":"2022-07-06","cited_by_count":0,"area":null},{"id":"2212.01565","title":"Leveraging Angular Information Between Feature and Classifier for Long-tailed Learning: A Prediction Reformulation Approach","created":"2022-12-03","cited_by_count":0,"area":null},{"id":"2507.08343","title":"Towards Imperceptible JPEG Image Hiding: Multi-range Representations-driven Adversarial Stego Generation","created":"2025-07-11","cited_by_count":0,"area":null},{"id":"2605.15916","title":"LoCO: Low-rank Compositional Rotation Fine-tuning","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2608.31036","title":"Normalized Low-Rank Adaptation","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}