{"total":69,"rows":[{"id":"2311.06243","title":"Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization","created":"2023-11-10","cited_by_count":114,"area":null},{"id":"2104.12753","title":"Vision Transformers with Patch Diversification","created":"2021-04-26","cited_by_count":45,"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":"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":"2104.02290","title":"Contrastive Syn-to-Real Generalization","created":"2021-04-06","cited_by_count":32,"area":null},{"id":"2303.08046","title":"Ultra-High-Resolution Detector Simulation with Intra-Event Aware GAN and Self-Supervised Relational Reasoning","created":"2023-03-07","cited_by_count":25,"area":null},{"id":"2103.15632","title":"Regular Polytope Networks","created":"2021-03-29","cited_by_count":24,"area":null},{"id":"2109.05565","title":"SphereFace Revived: Unifying Hyperspherical Face Recognition","created":"2021-09-12","cited_by_count":23,"area":null},{"id":"2205.12010","title":"SFace: Sigmoid-Constrained Hypersphere Loss for Robust Face Recognition","created":"2022-05-24","cited_by_count":21,"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":"2404.04316","title":"Parameter Efficient Quasi-Orthogonal Fine-Tuning via Givens Rotation","created":"2024-04-05","cited_by_count":21,"area":null},{"id":"2506.03133","title":"PoLAR: Polar-Decomposed Low-Rank Adapter Representation","created":"2025-06-03","cited_by_count":20,"area":null},{"id":"2202.04829","title":"Target-aware Molecular Graph Generation","created":"2022-02-10","cited_by_count":18,"area":null},{"id":"2206.00845","title":"Hyperspherical Consistency Regularization","created":"2022-06-02","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":"2210.05398","title":"Continual Learning by Modeling Intra-Class Variation","created":"2022-10-11","cited_by_count":12,"area":null},{"id":"2310.17622","title":"Combating Representation Learning Disparity with Geometric Harmonization","created":"2023-10-26","cited_by_count":11,"area":null},{"id":"2110.14432","title":"Iterative Teaching by Label Synthesis","created":"2021-10-27","cited_by_count":10,"area":null},{"id":"2311.02523","title":"UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition","created":"2023-11-04","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":"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":"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":"2405.18045","title":"Bridging Mini-Batch and Asymptotic Analysis in Contrastive Learning: From InfoNCE to Kernel-Based Losses","created":"2024-05-28","cited_by_count":7,"area":null},{"id":"2506.19847","title":"Orthogonal Finetuning Made Scalable","created":"2025-06-24","cited_by_count":7,"area":null},{"id":"2502.17130","title":"Low-distortion and GPU-compatible Tree Embeddings in Hyperbolic Space","created":"2025-02-24","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":"2107.09270","title":"Locality-aware Channel-wise Dropout for Occluded Face Recognition","created":"2021-07-20","cited_by_count":5,"area":null},{"id":"2206.11589","title":"Learning Towards the Largest Margins","created":"2022-06-23","cited_by_count":5,"area":null},{"id":"2212.08172","title":"Reliable Measures of Spread in High Dimensional Latent Spaces","created":"2022-12-15","cited_by_count":5,"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":"2409.11786","title":"Efficient Low-Resolution Face Recognition via Bridge Distillation","created":"2024-09-18","cited_by_count":5,"area":null},{"id":"2502.06916","title":"QuIC: Quantum-Inspired Compound Adapters for Parameter Efficient Fine-Tuning","created":"2025-02-10","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":"2105.00925","title":"Hyperspherically Regularized Networks for Self-Supervision","created":"2021-04-29","cited_by_count":4,"area":null},{"id":"2206.15204","title":"Data-Efficient Learning via Minimizing Hyperspherical Energy","created":"2022-06-30","cited_by_count":4,"area":null},{"id":"2209.04920","title":"Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognition","created":"2022-09-11","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":"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":"2505.16531","title":"HOFT: Householder Orthogonal Fine-tuning","created":"2025-05-22","cited_by_count":3,"area":null},{"id":"2506.04190","title":"How to Use Graph Data in the Wild to Help Graph Anomaly Detection?","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2510.04090","title":"Using predefined vector systems as latent space configuration for neural network supervised training on data with arbitrarily large number of classes","created":"2025-10-05","cited_by_count":3,"area":null},{"id":"2109.08839","title":"SpeechNAS: Towards Better Trade-off between Latency and Accuracy for Large-Scale Speaker Verification","created":"2021-09-18","cited_by_count":2,"area":null},{"id":"2112.05827","title":"Quality-Aware Multimodal Biometric Recognition","created":"2021-12-10","cited_by_count":2,"area":null},{"id":"2208.00789","title":"Self-supervised learning with rotation-invariant kernels","created":"2022-07-28","cited_by_count":2,"area":null},{"id":"2209.01275","title":"Feature diversity in self-supervised learning","created":"2022-09-02","cited_by_count":2,"area":null},{"id":"2212.11747","title":"Deep Simplex Classifier for Maximizing the Margin in Both Euclidean and Angular Spaces","created":"2022-12-22","cited_by_count":2,"area":null},{"id":"2405.17678","title":"TIMA: Text-Image Mutual Awareness for Balancing Zero-Shot Adversarial Robustness and Generalization Ability","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2502.11646","title":"Hyper-SET: Designing Transformers via Hyperspherical Energy Minimization","created":"2025-02-17","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":"2510.01172","title":"Energy-Regularized Sequential Model Editing on Hyperspheres","created":"2025-10-01","cited_by_count":2,"area":null},{"id":"2601.07873","title":"Multiplicative Orthogonal Sequential Editing for Language Models","created":"2026-01-11","cited_by_count":2,"area":null},{"id":"2502.08231","title":"Keep your distance: learning dispersed embeddings on $\\mathbb{S}_m$","created":"2025-02-12","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":"2509.16729","title":"Angular Dispersion Accelerates $k$-Nearest Neighbors Machine Translation","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2104.11610","title":"Eccentric Regularization: Minimizing Hyperspherical Energy without explicit projection","created":"2021-04-23","cited_by_count":0,"area":null},{"id":"2109.14798","title":"Introducing the DOME Activation Functions","created":"2021-09-30","cited_by_count":0,"area":null},{"id":"2206.10137","title":"Few-Max: Few-Shot Domain Adaptation for Unsupervised Contrastive Representation Learning","created":"2022-06-21","cited_by_count":0,"area":null},{"id":"2211.06843","title":"Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning","created":"2022-11-13","cited_by_count":0,"area":null},{"id":"2405.15157","title":"Rethinking Class-Incremental Learning from a Dynamic Imbalanced Learning Perspective","created":"2024-05-24","cited_by_count":0,"area":null},{"id":"2407.13392","title":"Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability","created":"2024-07-18","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":"2511.08360","title":"Extreme Model Compression with Structured Sparsity at Low Precision","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2602.17287","title":"Representation Collapse in Machine Translation Through the Lens of Angular Dispersion","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2609.24688","title":"Understanding Hyperspherical Geometry of ECAPA-TDNN Embedding and Its Impact on Zero-Shot Voice Conversion","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.37564","title":"Orthogonal Yet Coupled: Decoupling Geometric Components for Model Merging","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}