{"total":74,"rows":[{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417,"area":null},{"id":"2208.05512","title":"Imbalance Trouble: Revisiting Neural-Collapse Geometry","created":"2022-08-10","cited_by_count":80,"area":null},{"id":"2308.16898","title":"Transformers as Support Vector Machines","created":"2023-08-31","cited_by_count":74,"area":null},{"id":"2205.02215","title":"FedNest: Federated Bilevel, Minimax, and Compositional Optimization","created":"2022-05-04","cited_by_count":60,"area":null},{"id":"2306.13596","title":"Max-Margin Token Selection in Attention Mechanism","created":"2023-06-23","cited_by_count":58,"area":null},{"id":"2201.01212","title":"AutoBalance: Optimized Loss Functions for Imbalanced Data","created":"2022-01-04","cited_by_count":49,"area":null},{"id":"2208.13365","title":"Long-Tailed Classification of Thorax Diseases on Chest X-Ray: A New Benchmark Study","created":"2022-08-29","cited_by_count":45,"area":null},{"id":"2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","created":"2021-06-21","cited_by_count":42,"area":null},{"id":"2303.17093","title":"OpenMix: Exploring Outlier Samples for Misclassification Detection","created":"2023-03-30","cited_by_count":38,"area":null},{"id":"2403.08081","title":"Mechanics of Next Token Prediction with Self-Attention","created":"2024-03-12","cited_by_count":34,"area":null},{"id":"2308.12553","title":"Don't blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy","created":"2023-08-24","cited_by_count":30,"area":null},{"id":"2309.07418","title":"A Fast Optimization View: Reformulating Single Layer Attention in LLM Based on Tensor and SVM Trick, and Solving It in Matrix Multiplication Time","created":"2023-09-14","cited_by_count":30,"area":null},{"id":"2201.12293","title":"Understanding Why Generalized Reweighting Does Not Improve Over ERM","created":"2022-01-28","cited_by_count":29,"area":null},{"id":"2212.13827","title":"Escaping Saddle Points for Effective Generalization on Class-Imbalanced Data","created":"2022-12-28","cited_by_count":28,"area":null},{"id":"2406.00783","title":"AI-Face: A Million-Scale Demographically Annotated AI-Generated Face Dataset and Fairness Benchmark","created":"2024-06-02","cited_by_count":28,"area":null},{"id":"2407.08039","title":"Knowledge Overshadowing Causes Amalgamated Hallucination in Large Language Models","created":"2024-07-10","cited_by_count":25,"area":null},{"id":"2310.04752","title":"A Unified Perspective for Loss-Oriented Imbalanced Learning via Localization","created":"2023-10-07","cited_by_count":24,"area":null},{"id":"2303.07608","title":"On the Implicit Geometry of Cross-Entropy Parameterizations for Label-Imbalanced Data","created":"2023-03-14","cited_by_count":23,"area":null},{"id":"2112.12986","title":"Is Importance Weighting Incompatible with Interpolating Classifiers?","created":"2021-12-24","cited_by_count":19,"area":null},{"id":"2409.20398","title":"AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation","created":"2024-09-30","cited_by_count":18,"area":null},{"id":"2401.16164","title":"Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm","created":"2024-01-29","cited_by_count":16,"area":null},{"id":"2405.07780","title":"DirMixE: Harnessing Test Agnostic Long-tail Recognition with Hierarchical Label Variations","created":"2024-05-13","cited_by_count":15,"area":"moe"},{"id":"2502.10381","title":"Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Data","created":"2025-02-14","cited_by_count":15,"area":null},{"id":"2402.18551","title":"Implicit Optimization Bias of Next-Token Prediction in Linear Models","created":"2024-02-28","cited_by_count":14,"area":null},{"id":"2404.02900","title":"DeiT-LT Distillation Strikes Back for Vision Transformer Training on Long-Tailed Datasets","created":"2024-04-03","cited_by_count":14,"area":null},{"id":"2404.04517","title":"Latent-based Diffusion Model for Long-tailed Recognition","created":"2024-04-06","cited_by_count":14,"area":"diffusion"},{"id":"2505.01660","title":"Focal-SAM: Focal Sharpness-Aware Minimization for Long-Tailed Classification","created":"2025-05-03","cited_by_count":14,"area":null},{"id":"2206.02792","title":"FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data","created":"2022-06-06","cited_by_count":13,"area":null},{"id":"2107.04641","title":"Training Over-parameterized Models with Non-decomposable Objectives","created":"2021-07-09","cited_by_count":11,"area":null},{"id":"2510.23049","title":"Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients","created":"2025-10-27","cited_by_count":11,"area":"lr"},{"id":"2204.13208","title":"ELM: Embedding and Logit Margins for Long-Tail Learning","created":"2022-04-27","cited_by_count":10,"area":null},{"id":"2211.07096","title":"Alternating Implicit Projected SGD and Its Efficient Variants for Equality-constrained Bilevel Optimization","created":"2022-11-14","cited_by_count":10,"area":null},{"id":"2403.02886","title":"Revisiting Confidence Estimation: Towards Reliable Failure Prediction","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2306.03440","title":"Quantifying the Variability Collapse of Neural Networks","created":"2023-06-06","cited_by_count":9,"area":null},{"id":"2512.23947","title":"Improved Balanced Classification with Theoretically Grounded Loss Functions","created":"2025-12-30","cited_by_count":9,"area":null},{"id":"2206.01399","title":"Generalization for multiclass classification with overparameterized linear models","created":"2022-06-03","cited_by_count":8,"area":null},{"id":"2305.09938","title":"Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization","created":"2023-05-17","cited_by_count":8,"area":null},{"id":"2310.00893","title":"Engineering the Neural Collapse Geometry of Supervised-Contrastive Loss","created":"2023-10-02","cited_by_count":8,"area":null},{"id":"2505.16341","title":"A Square Peg in a Square Hole: Meta-Expert for Long-Tailed Semi-Supervised Learning","created":"2025-05-22","cited_by_count":7,"area":null},{"id":"2206.06479","title":"Robust Distillation for Worst-class Performance","created":"2022-06-13","cited_by_count":6,"area":"distill"},{"id":"2209.08745","title":"Importance Tempering: Group Robustness for Overparameterized Models","created":"2022-09-19","cited_by_count":6,"area":null},{"id":"2211.15724","title":"Malign Overfitting: Interpolation Can Provably Preclude Invariance","created":"2022-11-28","cited_by_count":6,"area":null},{"id":"2212.01007","title":"Compound Batch Normalization for Long-tailed Image Classification","created":"2022-12-02","cited_by_count":5,"area":null},{"id":"2505.02182","title":"Robust AI-Generated Face Detection with Imbalanced Data","created":"2025-05-04","cited_by_count":5,"area":null},{"id":"2206.12739","title":"On how to avoid exacerbating spurious correlations when models are overparameterized","created":"2022-06-25","cited_by_count":4,"area":null},{"id":"2303.07475","title":"General Loss Functions Lead to (Approximate) Interpolation in High Dimensions","created":"2023-03-13","cited_by_count":4,"area":null},{"id":"2311.14090","title":"Class Uncertainty: A Measure to Mitigate Class Imbalance","created":"2023-11-23","cited_by_count":4,"area":null},{"id":"2404.09779","title":"A replica analysis of under-bagging","created":"2024-04-15","cited_by_count":4,"area":null},{"id":"2205.13094","title":"Undersampling is a Minimax Optimal Robustness Intervention in Nonparametric Classification","created":"2022-05-26","cited_by_count":3,"area":null},{"id":"2405.06546","title":"Sharp analysis of out-of-distribution error for \"importance-weighted\" estimators in the overparameterized regime","created":"2024-05-10","cited_by_count":3,"area":null},{"id":"2410.02010","title":"MONICA: Benchmarking on Long-tailed Medical Image Classification","created":"2024-10-02","cited_by_count":3,"area":null},{"id":"2412.13715","title":"SSE-SAM: Balancing Head and Tail Classes Gradually through Stage-Wise SAM","created":"2024-12-18","cited_by_count":3,"area":null},{"id":"2204.09583","title":"Improved Group Robustness via Classifier Retraining on Independent Splits","created":"2022-04-20","cited_by_count":2,"area":null},{"id":"2401.14343","title":"Class-attribute Priors: Adapting Optimization to Heterogeneity and Fairness Objective","created":"2024-01-25","cited_by_count":2,"area":null},{"id":"2402.11742","title":"Balanced Data, Imbalanced Spectra: Unveiling Class Disparities with Spectral Imbalance","created":"2024-02-18","cited_by_count":2,"area":null},{"id":"2502.18218","title":"FLARE: A Framework for Stellar Flare Forecasting using Stellar Physical Properties and Historical Records","created":"2025-02-25","cited_by_count":2,"area":null},{"id":"2601.12011","title":"Why Loss Re-weighting Works If You Stop Early: Training Dynamics of Unconstrained Features","created":"2026-01-17","cited_by_count":2,"area":null},{"id":"2604.27723","title":"Optimized Deferral for Imbalanced Settings","created":"2026-04-30","cited_by_count":2,"area":null},{"id":"2310.18832","title":"Responsible AI (RAI) Games and Ensembles","created":"2023-10-28","cited_by_count":1,"area":null},{"id":"2409.05598","title":"When resampling/reweighting improves feature learning in imbalanced classification?: A toy-model study","created":"2024-09-09","cited_by_count":1,"area":null},{"id":"2409.17582","title":"Multiplicative Logit Adjustment Approximates Neural-Collapse-Aware Decision Boundary Adjustment","created":"2024-09-26","cited_by_count":1,"area":null},{"id":"2501.11638","title":"Class Imbalance in Anomaly Detection: Learning from an Exactly Solvable Model","created":"2025-01-20","cited_by_count":1,"area":null},{"id":"2505.18217","title":"ABHINAYA -- A System for Speech Emotion Recognition In Naturalistic Conditions Challenge","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2506.20025","title":"Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining","created":"2025-06-24","cited_by_count":1,"area":null},{"id":"2506.23280","title":"BAPE: Learning an Explicit Bayes Classifier for Long-tailed Visual Recognition","created":"2025-06-29","cited_by_count":1,"area":null},{"id":"2605.03221","title":"Synthetic Data Generation for Long-Tail Medical Image Classification: A Case Study in Skin Lesions","created":"2026-05-04","cited_by_count":1,"area":"diffusion"},{"id":"2310.14890","title":"Bounding the Worst-class Error: A Boosting Approach","created":"2023-10-20","cited_by_count":0,"area":null},{"id":"2402.05400","title":"Optimizing for ROC Curves on Class-Imbalanced Data by Training over a Family of Loss Functions","created":"2024-02-08","cited_by_count":0,"area":null},{"id":"2405.04903","title":"Imbalanced Graph Classification with Multi-scale Oversampling Graph Neural Networks","created":"2024-05-08","cited_by_count":0,"area":null},{"id":"2409.04101","title":"Ultra-imbalanced classification guided by statistical information","created":"2024-09-06","cited_by_count":0,"area":null},{"id":"2410.03588","title":"Training Over a Distribution of Hyperparameters for Enhanced Performance and Adaptability on Imbalanced Classification","created":"2024-10-04","cited_by_count":0,"area":null},{"id":"2410.22883","title":"Dataset Awareness is not Enough: Implementing Sample-level Tail Encouragement in Long-tailed Self-supervised Learning","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2502.16948","title":"Deep Minimax Classifiers for Imbalanced Datasets with a Small Number of Minority Samples","created":"2025-02-24","cited_by_count":0,"area":null},{"id":"2609.39177","title":"Whitening Improves Robustness to Spurious Correlations in Linear Probes","created":"2026-09-30","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}