equiangular tight frame

Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data JMLR 2026 Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models CVPR 2026 Detecting Unknown Objects via Energy-based Separation for Open World Object Detection CVPR 2026 Geometry-driven OOD Detectors Are Class-Incremental Learners CVPR 2026 GOAL: Geometrically Optimal Alignment for Continual Generalized Category Discovery AAAI 2026 POUR: A Provably Optimal Method for Unlearning Representation via Neural Collapse CVPR 2026 MLC-NC: Long-Tailed Multi-Label Image Classification Through the Lens of Neural Collapse AAAI 2025 Learning Equi-angular Representations for Online Continual Learning CVPR 2024 Neural Collapse for Cross-entropy Class-Imbalanced Learning with Unconstrained ReLU Features Model ICML 2024 Neural Collapse in Multi-label Learning with Pick-all-label Loss ICML 2024 Early Exit with Disentangled Representation and Equiangular Tight Frame ACL 2023 Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path ICLR 2022