{"total":55,"rows":[{"id":"2306.07280","title":"Controlling Text-to-Image Diffusion by Orthogonal Finetuning","created":"2023-06-12","cited_by_count":208,"area":"diffusion"},{"id":"2111.13839","title":"Towards Principled Disentanglement for Domain Generalization","created":"2021-11-27","cited_by_count":91,"area":null},{"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":"2103.14021","title":"Orthogonal Projection Loss","created":"2021-03-25","cited_by_count":44,"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":"2502.15280","title":"Hyperspherical Normalization for Scalable Deep Reinforcement Learning","created":"2025-02-21","cited_by_count":38,"area":"deeprl"},{"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":"2412.01095","title":"VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models","created":"2024-12-02","cited_by_count":24,"area":"mllm"},{"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":"2206.00845","title":"Hyperspherical Consistency Regularization","created":"2022-06-02","cited_by_count":16,"area":null},{"id":"2306.16248","title":"Latent SDEs on Homogeneous Spaces","created":"2023-06-28","cited_by_count":16,"area":null},{"id":"2208.01188","title":"Curved Geometric Networks for Visual Anomaly Recognition","created":"2022-08-02","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":"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":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2111.05476","title":"Learning to Disentangle Scenes for Person Re-identification","created":"2021-11-10","cited_by_count":10,"area":null},{"id":"2502.10706","title":"Raising the Bar in Graph OOD Generalization: Invariant Learning Beyond Explicit Environment Modeling","created":"2025-02-15","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":"2510.00537","title":"Spectral Scaling Laws in Language Models: How Effectively Do Feed-Forward Networks Use Their Latent Space?","created":"2025-10-01","cited_by_count":8,"area":null},{"id":"2207.08525","title":"Angular Gap: Reducing the Uncertainty of Image Difficulty through Model Calibration","created":"2022-07-18","cited_by_count":6,"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":"2409.11786","title":"Efficient Low-Resolution Face Recognition via Bridge Distillation","created":"2024-09-18","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":"2303.05066","title":"Distortion-Disentangled Contrastive Learning","created":"2023-03-09","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":"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":"2603.06922","title":"NerVE: Nonlinear Eigenspectrum Dynamics in LLM Feed-Forward Networks","created":"2026-03-06","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":"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":"2510.06907","title":"Angular Constraint Embedding via SpherePair Loss for Constrained Clustering","created":"2025-10-08","cited_by_count":2,"area":null},{"id":"2605.28902","title":"Orthogonal Concept Erasure for Diffusion Models","created":"2026-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2207.03206","title":"Leveraging Log Instructions in Log-based Anomaly Detection","created":"2022-07-07","cited_by_count":1,"area":null},{"id":"2211.08486","title":"Scalar Invariant Networks with Zero Bias","created":"2022-11-15","cited_by_count":1,"area":null},{"id":"2310.00299","title":"RelBERT: Embedding Relations with Language Models","created":"2023-09-30","cited_by_count":1,"area":null},{"id":"2502.10423","title":"Spiking Neural Network Feature Discrimination Boosts Modality Fusion","created":"2025-02-05","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":"2109.14746","title":"Improvising the Learning of Neural Networks on Hyperspherical Manifold","created":"2021-09-29","cited_by_count":0,"area":null},{"id":"2201.02991","title":"A Survey on Face Recognition Systems","created":"2022-01-09","cited_by_count":0,"area":null},{"id":"2206.09616","title":"Revisiting lp-constrained Softmax Loss: A Comprehensive Study","created":"2022-06-20","cited_by_count":0,"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":"2212.12649","title":"Hyperspherical Loss-Aware Ternary Quantization","created":"2022-12-24","cited_by_count":0,"area":null},{"id":"2212.12651","title":"Pruning On-the-Fly: A Recoverable Pruning Method without Fine-tuning","created":"2022-12-24","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":"2507.04310","title":"Heterogeneous Federated Learning with Prototype Alignment and Upscaling","created":"2025-07-06","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":"2608.01284","title":"Training nGPT","created":"2026-08-02","cited_by_count":0,"area":"moe"},{"id":"2608.31036","title":"Normalized Low-Rank Adaptation","created":"2026-08-31","cited_by_count":0,"area":null}],"next_cursor":null}