{"total":95,"rows":[{"id":"2303.10058","title":"No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier","created":"2023-03-17","cited_by_count":55,"area":null},{"id":"2209.09211","title":"Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold","created":"2022-09-19","cited_by_count":50,"area":null},{"id":"2505.23883","title":"BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning","created":"2025-05-29","cited_by_count":50,"area":null},{"id":"2305.13165","title":"Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model","created":"2023-05-22","cited_by_count":43,"area":null},{"id":"2310.06823","title":"NECO: NEural Collapse Based Out-of-distribution detection","created":"2023-10-10","cited_by_count":42,"area":null},{"id":"2309.09725","title":"Neural Collapse for Unconstrained Feature Model under Cross-entropy Loss with Imbalanced Data","created":"2023-09-18","cited_by_count":38,"area":null},{"id":"2405.17767","title":"Linguistic Collapse: Neural Collapse in (Large) Language Models","created":"2024-05-28","cited_by_count":38,"area":null},{"id":"2210.16658","title":"Perturbation Analysis of Neural Collapse","created":"2022-10-29","cited_by_count":35,"area":null},{"id":"2310.12244","title":"A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm","created":"2023-10-18","cited_by_count":33,"area":null},{"id":"2505.10465","title":"Superposition Yields Robust Neural Scaling","created":"2025-05-15","cited_by_count":31,"area":"mechinterp"},{"id":"2210.15435","title":"Grokking phase transitions in learning local rules with gradient descent","created":"2022-10-26","cited_by_count":28,"area":null},{"id":"2302.12453","title":"Inducing Neural Collapse in Deep Long-tailed Learning","created":"2023-02-24","cited_by_count":28,"area":null},{"id":"2212.12206","title":"Understanding and Improving Transfer Learning of Deep Models via Neural Collapse","created":"2022-12-23","cited_by_count":24,"area":null},{"id":"2402.13728","title":"Average gradient outer product as a mechanism for deep neural collapse","created":"2024-02-21","cited_by_count":22,"area":null},{"id":"2409.04180","title":"The Prevalence of Neural Collapse in Neural Multivariate Regression","created":"2024-09-06","cited_by_count":21,"area":null},{"id":"2306.01154","title":"The Law of Parsimony in Gradient Descent for Learning Deep Linear Networks","created":"2023-06-01","cited_by_count":20,"area":null},{"id":"2307.01951","title":"A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks","created":"2023-07-04","cited_by_count":19,"area":null},{"id":"2305.16427","title":"Neural (Tangent Kernel) Collapse","created":"2023-05-25","cited_by_count":18,"area":null},{"id":"2312.02517","title":"Simplifying Neural Network Training Under Class Imbalance","created":"2023-12-05","cited_by_count":18,"area":null},{"id":"2405.14468","title":"Neural Collapse versus Low-rank Bias: Is Deep Neural Collapse Really Optimal?","created":"2024-05-23","cited_by_count":17,"area":null},{"id":"2310.15903","title":"Neural Collapse in Multi-label Learning with Pick-all-label Loss","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2210.10041","title":"Hidden State Variability of Pretrained Language Models Can Guide Computation Reduction for Transfer Learning","created":"2022-10-18","cited_by_count":13,"area":null},{"id":"2410.23169","title":"The Persistence of Neural Collapse Despite Low-Rank Bias","created":"2024-10-30","cited_by_count":13,"area":null},{"id":"2405.00985","title":"Progressive Feedforward Collapse of ResNet Training","created":"2024-05-02","cited_by_count":12,"area":null},{"id":"2405.17816","title":"Pursuing Feature Separation based on Neural Collapse for Out-of-Distribution Detection","created":"2024-05-28","cited_by_count":12,"area":null},{"id":"2304.02912","title":"Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach","created":"2023-04-06","cited_by_count":11,"area":null},{"id":"2502.10691","title":"Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning","created":"2025-02-15","cited_by_count":11,"area":null},{"id":"2409.01832","title":"Beyond Unconstrained Features: Neural Collapse for Shallow Neural Networks with General Data","created":"2024-09-03","cited_by_count":10,"area":null},{"id":"2410.03006","title":"Formation of Representations in Neural Networks","created":"2024-10-03","cited_by_count":10,"area":null},{"id":"2309.04644","title":"Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay","created":"2023-09-09","cited_by_count":9,"area":null},{"id":"2406.18854","title":"What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networks","created":"2024-06-27","cited_by_count":9,"area":null},{"id":"2406.03057","title":"BWS: Best Window Selection Based on Sample Scores for Data Pruning across Broad Ranges","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2510.11709","title":"Adversarial Attacks Leverage Interference Between Features in Superposition","created":"2025-10-13","cited_by_count":8,"area":null},{"id":"2310.08358","title":"Towards Demystifying the Generalization Behaviors When Neural Collapse Emerges","created":"2023-10-12","cited_by_count":7,"area":null},{"id":"2402.06171","title":"Pushing Boundaries: Mixup's Influence on Neural Collapse","created":"2024-02-09","cited_by_count":7,"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":"2410.04959","title":"Collapse-Proof Non-Contrastive Self-Supervised Learning","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2401.13558","title":"Task structure and nonlinearity jointly determine learned representational geometry","created":"2024-01-24","cited_by_count":6,"area":null},{"id":"2402.06751","title":"Low-Rank Learning by Design: the Role of Network Architecture and Activation Linearity in Gradient Rank Collapse","created":"2024-02-09","cited_by_count":5,"area":null},{"id":"2509.12249","title":"Why and How Auxiliary Tasks Improve JEPA Representations","created":"2025-09-12","cited_by_count":5,"area":null},{"id":"2402.18905","title":"Characterizing the Training Dynamics of Private Fine-tuning with Langevin diffusion","created":"2024-02-29","cited_by_count":4,"area":null},{"id":"2405.15706","title":"The Impact of Geometric Complexity on Neural Collapse in Transfer Learning","created":"2024-05-24","cited_by_count":4,"area":null},{"id":"2406.02105","title":"Can Kernel Methods Explain How the Data Affects Neural Collapse?","created":"2024-06-04","cited_by_count":4,"area":null},{"id":"2506.01599","title":"Connecting Neural Models Latent Geometries with Relative Geodesic Representations","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2603.29805","title":"From Density Matrices to Phase Transitions in Deep Learning: Spectral Early Warnings and Interpretability","created":"2026-03-31","cited_by_count":4,"area":null},{"id":"2311.03055","title":"DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework","created":"2023-11-06","cited_by_count":3,"area":null},{"id":"2312.07841","title":"On the Dynamics Under the Unhinged Loss and Beyond","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2410.08451","title":"The Proof of Kolmogorov-Arnold May Illuminate Neural Network Learning","created":"2024-10-11","cited_by_count":3,"area":null},{"id":"2410.23391","title":"Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective","created":"2024-10-30","cited_by_count":3,"area":null},{"id":"2505.13471","title":"The Spotlight Resonance Method: Resolving the Alignment of Embedded Activations","created":"2025-05-09","cited_by_count":3,"area":null},{"id":"2512.01766","title":"On the Unreasonable Effectiveness of Last-layer Retraining","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2206.05530","title":"Memorization-Dilation: Modeling Neural Collapse Under Label Noise","created":"2022-06-11","cited_by_count":2,"area":null},{"id":"2404.01397","title":"Object-conditioned Bag of Instances for Few-Shot Personalized Instance Recognition","created":"2024-04-01","cited_by_count":2,"area":null},{"id":"2405.17181","title":"Spectral regularization for adversarially-robust representation learning","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2408.15894","title":"The Role of Fibration Symmetries in Geometric Deep Learning","created":"2024-08-28","cited_by_count":2,"area":null},{"id":"2410.04264","title":"Decoupling Dynamical Richness from Representation Learning: Towards Practical Measurement","created":"2024-10-05","cited_by_count":2,"area":null},{"id":"2507.05644","title":"The Features at Convergence Theorem: a first-principles alternative to the Neural Feature Ansatz for how networks learn representations","created":"2025-07-08","cited_by_count":2,"area":null},{"id":"2509.14001","title":"MOCHA: Multi-modal Objects-aware Cross-arcHitecture Alignment","created":"2025-09-17","cited_by_count":2,"area":null},{"id":"2512.04006","title":"Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics","created":"2025-12-03","cited_by_count":2,"area":null},{"id":"2604.00230","title":"Neural Collapse Dynamics: Depth, Activation, Regularisation, and Feature Norm Threshold","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2305.09556","title":"Adapting Sentence Transformers for the Aviation Domain","created":"2023-05-16","cited_by_count":1,"area":null},{"id":"2407.05843","title":"Evaluating the Fairness of Neural Collapse in Medical Image Classification","created":"2024-07-08","cited_by_count":1,"area":null},{"id":"2411.12914","title":"Trojan Cleansing with Neural Collapse","created":"2024-11-19","cited_by_count":1,"area":"safety"},{"id":"2503.06385","title":"A Good Start Matters: Enhancing Continual Learning with Data-Driven Weight Initialization","created":"2025-03-09","cited_by_count":1,"area":null},{"id":"2505.05813","title":"BCE vs. CE in Deep Feature Learning","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2507.08905","title":"Last Layer Hamiltonian Monte Carlo","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2507.14980","title":"FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios","created":"2025-07-20","cited_by_count":1,"area":null},{"id":"2507.19680","title":"Feature learning is decoupled from generalization in high capacity neural networks","created":"2025-07-25","cited_by_count":1,"area":null},{"id":"2508.15086","title":"Wormhole Dynamics in Deep Neural Networks","created":"2025-08-20","cited_by_count":1,"area":null},{"id":"2511.13539","title":"BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse","created":"2025-11-17","cited_by_count":1,"area":null},{"id":"2512.00391","title":"From Coefficients to Directions: Rethinking Model Merging with Directional Alignment","created":"2025-11-29","cited_by_count":1,"area":null},{"id":"2606.12488","title":"A Stationary (and Therefore Compatible) Representation is All You Need","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2607.11666","title":"How to Tame Grokking: Representation Geometry as a Control Signal","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2210.05422","title":"Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization","created":"2022-10-11","cited_by_count":0,"area":null},{"id":"2310.01770","title":"A simple connection from loss flatness to compressed neural representations","created":"2023-10-03","cited_by_count":0,"area":null},{"id":"2312.14427","title":"GROOD: GRadient-Aware Out-of-Distribution Detection","created":"2023-12-22","cited_by_count":0,"area":null},{"id":"2407.10702","title":"Geometric Analysis of Unconstrained Feature Models with $d=K$","created":"2024-07-15","cited_by_count":0,"area":null},{"id":"2410.21656","title":"Dimensionality-induced information loss of outliers in deep neural networks","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2411.00328","title":"How many classifiers do we need?","created":"2024-11-01","cited_by_count":0,"area":null},{"id":"2411.09250","title":"Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning","created":"2024-11-14","cited_by_count":0,"area":null},{"id":"2501.02616","title":"Multi-layer Radial Basis Function Networks for Out-of-distribution Detection","created":"2025-01-05","cited_by_count":0,"area":null},{"id":"2503.14572","title":"Robust Weight Imprinting: Insights from Neural Collapse and Proxy-Based Aggregation","created":"2025-03-18","cited_by_count":0,"area":null},{"id":"2505.11669","title":"OT Score: An OT based Confidence Score for Prototype-Assisted Source Free Unsupervised Domain Adaptation","created":"2025-05-16","cited_by_count":0,"area":null},{"id":"2505.14846","title":"Open-Set Semi-Supervised Learning for Long-Tailed Medical Datasets","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2512.21447","title":"An Equivariance Toolbox for Learning Dynamics","created":"2025-12-24","cited_by_count":0,"area":null},{"id":"2605.02183","title":"Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment","created":"2026-05-04","cited_by_count":0,"area":null},{"id":"2605.11291","title":"Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.11939","title":"Cluster-Aware Neural Collapse Prompt Tuning for Long-Tailed Generalization of Vision-Language Models","created":"2026-05-12","cited_by_count":0,"area":"mllm"},{"id":"2605.23087","title":"The Implicit Bias of Depth: From Neural Collapse to Softmax Codes","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2606.00344","title":"The role of class encoding in neural collapse","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.11319","title":"Learning from almost nothing: How neural networks survive heavy input corruption","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.07438","title":"Two-Stage Multi-Modal Fusion with Adaptive Alignment for Action Quality Assessment","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.12916","title":"Contrastive-Collapsed Loss for Flexible and Geometrically Optimal Embeddings and Faster Convergence","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2609.01014","title":"Low-Quality Face Recognition using Center Aligned Representations and Local Margin Constraints","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.35020","title":"Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}