No article text was recorded for this version.
neural collapse
Version 2 of 2121 papers151 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
- Blog: NECO: NEural Collapse Based Out-of-distribution detection
- Blog: Are All Losses Created Equal: A Neural Collapse Perspective
- Blog: Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
- Blog: BCE vs. CE in Deep Feature Learning
- Blog: Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
- Blog: Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
- Blog: Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs
- Blog: Extended Unconstrained Features Model for Exploring Deep Neural Collapse
- Blog: Hard-Negative Sampling for Contrastive Learning: Optimal Representation Geometry and Neural- vs Dimensional-Collapse
- Blog: Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
- Blog: Compress to One Point: Neural Collapse for Pre-Trained Model-Based Class-Incremental Learning
- Blog: Prevalence of Neural Collapse during the terminal phase of deep learning training
- Blog: Dissecting Supervised Constrastive Learning
- Blog: Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
- Blog: MASIL: Towards Maximum Separable Class Representation for Few Shot Class Incremental Learning
- Blog: UCDSC: Open Set UnCertainty aware Deep Simplex Classifier for Medical Image Datasets
- Blog: Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers
- Blog: EPA: Neural Collapse Inspired Robust Out-of-Distribution Detector
- Blog: Instructing Text-to-Image Diffusion Models via Classifier-Guided Semantic Optimization
- Blog: On the Role of Neural Collapse in Transfer Learning
- Blog: BCE vs. CE in Deep Feature Learning
- Blog: Breaking Inter-Layer Co-Adaptation by Classifier Anonymization
- Blog: Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?
- Blog: Do More Negative Samples Necessarily Hurt In Contrastive Learning?
- Blog: Cross Entropy versus Label Smoothing: A Neural Collapse Perspective
- Blog: Self-Supervised Contrastive Learning is Approximately Supervised Contrastive Learning
- Blog: Average gradient outer product as a mechanism for deep neural collapse
- Blog: Neural Collapse Under MSE Loss: Proximity to and Dynamics on the Central Path
- Blog: On the Robustness of Neural Collapse and the Neural Collapse of Robustness
- Blog: Trojan Cleansing with Neural Collapse
- Blog: Feature learning in deep classifiers through Intermediate Neural Collapse
- Blog: Unveiling the Dynamics of Information Interplay in Supervised Learning
- Blog: Neural Collapse with Normalized Features: A Geometric Analysis over the Riemannian Manifold
- Blog: Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection
- Blog: Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
- Blog: No Fear of Classifier Biases: Neural Collapse Inspired Federated Learning with Synthetic and Fixed Classifier
- Blog: Minimizing Chebyshev Prototype Risk Magically Mitigates the Perils of Overfitting
- Blog: BootOOD: Self-Supervised Out-of-Distribution Detection via Synthetic Sample Exposure under Neural Collapse
- Blog: POUR: A Provably Optimal Method for Unlearning Representations via Neural Collapse
- Blog: Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Training
- Blog: Wide Neural Networks Trained with Weight Decay Provably Exhibit Neural Collapse
- Blog: The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
- Blog: Revealing the Structure of Deep Neural Networks via Convex Duality
- Blog: Generalization Bounds for Transfer Learning with Pretrained Classifiers
- Blog: The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
- Blog: Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
- Blog: On the Optimization Landscape of Neural Collapse under MSE Loss: Global Optimality with Unconstrained Features
- Blog: A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning
- Blog: Towards understanding neural collapse in supervised contrastive learning with the information bottleneck method
- Blog: CoReS: Compatible Representations via Stationarity
- Blog: How Can Reliability of Artificial Intelligence Be Ensured?
- Blog: Neural Collapse Beyond the Unconstrained Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
- Blog: Neural Collapse Beyond the Unconstrainted Features Model: Landscape, Dynamics, and Generalization in the Mean-Field Regime
- Blog: Diagonalizing the Softmax: Hadamard Initialization for Tractable Cross-Entropy Dynamics
- Blog: Towards Understanding Neural Collapse: The Effects of Batch Normalization and Weight Decay
- Blog: Do More Negative Samples Necessarily Hurt In Contrastive Learning?
- Blog: All-around Neural Collapse for Imbalanced Classification
- Blog: Rethinking Loss Reweighting for Imbalance Learning as an Inverse Problem: A Neural Collapse Point of View
- Blog: Get the Best of Both Worlds: Improving Accuracy and Transferability by Grassmann Class Representation
Showing 60 of 121 papers.
History & citation
Current · Permanent link
- Geometric Convergence of Features in Neural Collapse merged into this direction (50% overlap)
- Neural Collapse and the Geometry of Deep Learning merged into this direction (56% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_neural_collapse_1f77ee60,
title = {neural collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/neural-collapse/rdr_1f77ee6049104a57b4145e71f319efb2},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 2, frozen text):
@misc{lacuna_neural_collapse_1f77ee60_v2,
title = {neural collapse},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/neural-collapse/rdr_1f77ee6049104a57b4145e71f319efb2/v/2},
note = {Version 2, frozen 2026-10-04. Accessed 2026-11-20},
}