{"list":"other","total":96,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"2303.12712","title":"Sparks of Artificial General Intelligence: Early experiments with GPT-4","created":"2023-03-22","cited_by_count":2592},{"id":"2206.07682","title":"Emergent Abilities of Large Language Models","created":"2022-06-15","cited_by_count":2512},{"id":"2111.09543","title":"DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing","created":"2021-11-18","cited_by_count":1254},{"id":"1901.05555","title":"Class-Balanced Loss Based on Effective Number of Samples","created":"2019-01-16","cited_by_count":1245},{"id":"1906.07413","title":"Learning Imbalanced Datasets with Label-Distribution-Aware Margin Loss","created":"2019-06-18","cited_by_count":989},{"id":"1705.08500","title":"Selective Classification for Deep Neural Networks","created":"2017-05-23","cited_by_count":852},{"id":"1910.09217","title":"Decoupling Representation and Classifier for Long-Tailed Recognition","created":"2019-10-21","cited_by_count":809},{"id":"1904.05160","title":"Large-Scale Long-Tailed Recognition in an Open World","created":"2019-04-10","cited_by_count":705},{"id":"1706.08498","title":"Spectrally-normalized margin bounds for neural networks","created":"2017-06-26","cited_by_count":686},{"id":"2007.07314","title":"Long-tail learning via logit adjustment","created":"2020-07-14","cited_by_count":618},{"id":"2110.04596","title":"Deep Long-Tailed Learning: A Survey","created":"2021-10-09","cited_by_count":417},{"id":"1912.02413","title":"BBN: Bilateral-Branch Network with Cumulative Learning for Long-Tailed Visual Recognition","created":"2019-12-05","cited_by_count":403},{"id":"2007.10740","title":"Balanced Meta-Softmax for Long-Tailed Visual Recognition","created":"2020-07-21","cited_by_count":400},{"id":"1802.06309","title":"Learning Adversarially Fair and Transferable Representations","created":"2018-02-17","cited_by_count":353},{"id":"1901.09192","title":"SelectiveNet: A Deep Neural Network with an Integrated Reject Option","created":"2019-01-26","cited_by_count":350},{"id":"1503.00036","title":"Norm-Based Capacity Control in Neural Networks","created":"2015-02-27","cited_by_count":299},{"id":"2003.05176","title":"Equalization Loss for Long-Tailed Object Recognition","created":"2020-03-11","cited_by_count":285},{"id":"2006.01862","title":"Consistent Estimators for Learning to Defer to an Expert","created":"2020-06-02","cited_by_count":271},{"id":"2010.01809","title":"Long-tailed Recognition by Routing Diverse Distribution-Aware Experts","created":"2020-10-05","cited_by_count":271},{"id":"2009.12991","title":"Long-Tailed Classification by Keeping the Good and Removing the Bad Momentum Causal Effect","created":"2020-09-28","cited_by_count":256},{"id":"2107.12028","title":"Parametric Contrastive Learning","created":"2021-07-26","cited_by_count":217},{"id":"2104.00466","title":"Improving Calibration for Long-Tailed Recognition","created":"2021-04-01","cited_by_count":212},{"id":"2304.07288","title":"Cross-Entropy Loss Functions: Theoretical Analysis and Applications","created":"2023-04-14","cited_by_count":210},{"id":"2001.01536","title":"Learning From Multiple Experts: Self-paced Knowledge Distillation for Long-tailed Classification","created":"2020-01-06","cited_by_count":175},{"id":"2012.00321","title":"Disentangling Label Distribution for Long-tailed Visual Recognition","created":"2020-12-01","cited_by_count":172},{"id":"2501.15383","title":"Qwen2.5-1M Technical Report","created":"2025-01-26","cited_by_count":164},{"id":"2003.10780","title":"Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective","created":"2020-03-24","cited_by_count":143},{"id":"1605.00251","title":"A vector-contraction inequality for Rademacher complexities","created":"2016-05-01","cited_by_count":142},{"id":"2005.00582","title":"Learning to Complement Humans","created":"2020-05-01","cited_by_count":124},{"id":"1903.12220","title":"The Algorithmic Automation Problem: Prediction, Triage, and Human Effort","created":"2019-03-28","cited_by_count":101},{"id":"2203.09081","title":"Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?","created":"2022-03-17","cited_by_count":100},{"id":"2101.10633","title":"ResLT: Residual Learning for Long-tailed Recognition","created":"2021-01-26","cited_by_count":96},{"id":"2107.09249","title":"Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition","created":"2021-07-20","cited_by_count":95},{"id":"1901.07590","title":"Striking the Right Balance with Uncertainty","created":"2019-01-22","cited_by_count":79},{"id":"2001.01385","title":"Identifying and Compensating for Feature Deviation in Imbalanced Deep Learning","created":"2020-01-06","cited_by_count":76},{"id":"2103.08902","title":"Differentiable Learning Under Triage","created":"2021-03-16","cited_by_count":76},{"id":"2103.01550","title":"Label-Imbalanced and Group-Sensitive Classification under Overparameterization","created":"2021-03-02","cited_by_count":74},{"id":"2102.13004","title":"Towards Unbiased and Accurate Deferral to Multiple Experts","created":"2021-02-25","cited_by_count":72},{"id":"2301.06197","title":"Who Should Predict? Exact Algorithms For Learning to Defer to Humans","created":"2023-01-15","cited_by_count":70},{"id":"2109.03216","title":"Learning Fast Sample Re-weighting Without Reward Data","created":"2021-09-07","cited_by_count":69},{"id":"2202.03673","title":"Calibrated Learning to Defer with One-vs-All Classifiers","created":"2022-02-08","cited_by_count":69},{"id":"2106.09859","title":"RSG: A Simple but Effective Module for Learning Imbalanced Datasets","created":"2021-06-18","cited_by_count":61},{"id":"2210.16955","title":"Learning to Defer to Multiple Experts: Consistent Surrogate Losses, Confidence Calibration, and Conformal Ensembles","created":"2022-10-30","cited_by_count":60},{"id":"2309.10019","title":"Long-Tail Learning with Foundation Model: Heavy Fine-Tuning Hurts","created":"2023-09-18","cited_by_count":58},{"id":"1607.01097","title":"AdaNet: Adaptive Structural Learning of Artificial Neural Networks","created":"2016-07-05","cited_by_count":54},{"id":"2010.11820","title":"Posterior Re-calibration for Imbalanced Datasets","created":"2020-10-22","cited_by_count":53},{"id":"1705.08826","title":"Learning with Average Top-k Loss","created":"2017-05-24","cited_by_count":52},{"id":"2207.09584","title":"Sample Efficient Learning of Predictors that Complement Humans","created":"2022-07-19","cited_by_count":46},{"id":"1909.02963","title":"Regression Under Human Assistance","created":"2019-09-06","cited_by_count":40},{"id":"2310.14774","title":"Principled Approaches for Learning to Defer with Multiple Experts","created":"2023-10-23","cited_by_count":38},{"id":"2310.14772","title":"Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithms","created":"2023-10-23","cited_by_count":36},{"id":"2110.15403","title":"Selective Regression Under Fairness Criteria","created":"2021-10-28","cited_by_count":34},{"id":"2301.09044","title":"Learning to Reject with a Fixed Predictor: Application to Decontextualization","created":"2023-01-22","cited_by_count":32},{"id":"2310.08106","title":"Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models","created":"2023-10-12","cited_by_count":32},{"id":"2310.14770","title":"Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstention","created":"2023-10-23","cited_by_count":32},{"id":"2006.16597","title":"Regression with reject option and application to kNN","created":"2020-06-30","cited_by_count":30},{"id":"2403.19494","title":"Regression with Multi-Expert Deferral","created":"2024-03-28","cited_by_count":29},{"id":"2307.02035","title":"Ranking with Abstention","created":"2023-07-05","cited_by_count":27},{"id":"2403.02683","title":"Learning to Defer to a Population: A Meta-Learning Approach","created":"2024-03-05","cited_by_count":27},{"id":"2407.13732","title":"Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer","created":"2024-07-18","cited_by_count":26},{"id":"2405.05968","title":"A Universal Growth Rate for Learning with Smooth Surrogate Losses","created":"2024-05-09","cited_by_count":24},{"id":"2407.07140","title":"Cardinality-Aware Set Prediction and Top-$k$ Classification","created":"2024-07-09","cited_by_count":23},{"id":"2407.13746","title":"Multi-Label Learning with Stronger Consistency Guarantees","created":"2024-07-18","cited_by_count":22},{"id":"2206.08704","title":"Maximum Class Separation as Inductive Bias in One Matrix","created":"2022-06-17","cited_by_count":21},{"id":"2403.19480","title":"$H$-Consistency Guarantees for Regression","created":"2024-03-28","cited_by_count":21},{"id":"2101.05360","title":"Preferential Mixture-of-Experts: Interpretable Models that Rely on Human Expertise as much as Possible","created":"2021-01-13","cited_by_count":19},{"id":"1605.06443","title":"Structured Prediction Theory Based on Factor Graph Complexity","created":"2016-05-20","cited_by_count":18},{"id":"1804.02246","title":"Adaptive Cost-sensitive Online Classification","created":"2018-04-06","cited_by_count":18},{"id":"2407.13722","title":"Enhanced $H$-Consistency Bounds","created":"2024-07-18","cited_by_count":18},{"id":"2108.07392","title":"Incorporating Uncertainty in Learning to Defer Algorithms for Safe Computer-Aided Diagnosis","created":"2021-08-17","cited_by_count":17},{"id":"2410.15729","title":"A Two-Stage Learning-to-Defer Approach for Multi-Task Learning","created":"2024-10-21","cited_by_count":17},{"id":"2502.01027","title":"Adversarial Robustness in Two-Stage Learning-to-Defer: Algorithms and Guarantees","created":"2025-02-03","cited_by_count":16},{"id":"2506.20650","title":"Mastering Multiple-Expert Routing: Realizable $H$-Consistency and Strong Guarantees for Learning to Defer","created":"2025-06-25","cited_by_count":16},{"id":"2410.15761","title":"Optimal Query Allocation in Extractive QA with LLMs: A Learning-to-Defer Framework with Theoretical Guarantees","created":"2024-10-21","cited_by_count":15},{"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},{"id":"2402.13505","title":"SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning","created":"2024-02-21","cited_by_count":14},{"id":"2405.09782","title":"Size-invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection","created":"2024-05-16","cited_by_count":14},{"id":"2510.26706","title":"Budgeted Multiple-Expert Deferral","created":"2025-10-30","cited_by_count":13},{"id":"2112.10768","title":"Improving Learning-to-Defer Algorithms Through Fine-Tuning","created":"2021-12-18","cited_by_count":11},{"id":"2305.18732","title":"Wrapped Cauchy Distributed Angular Softmax for Long-Tailed Visual Recognition","created":"2023-05-30","cited_by_count":11},{"id":"2310.12152","title":"Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection","created":"2023-10-18","cited_by_count":11},{"id":"2311.04550","title":"Regression with Cost-based Rejection","created":"2023-11-08","cited_by_count":11},{"id":"1911.07498","title":"Online Adaptive Asymmetric Active Learning with Limited Budgets","created":"2019-11-18","cited_by_count":10},{"id":"2406.02435","title":"Generative Active Learning for Long-tailed Instance Segmentation","created":"2024-06-04","cited_by_count":10},{"id":"2512.23947","title":"Improved Balanced Classification with Theoretically Grounded Loss Functions","created":"2025-12-30","cited_by_count":9},{"id":"2512.22886","title":"Theory and Algorithms for Learning with Multi-Class Abstention and Multi-Expert Deferral","created":"2025-12-28","cited_by_count":8},{"id":"2504.12988","title":"Why Ask One When You Can Ask $k$? Learning-to-Defer to the Top-$k$ Experts","created":"2025-04-17","cited_by_count":7},{"id":"2511.15816","title":"Beyond Tsybakov: Model Margin Noise and $\\mathcal{H}$-Consistency Bounds","created":"2025-11-19","cited_by_count":7},{"id":"2512.22880","title":"Fundamental Novel Consistency Theory: $H$-Consistency Bounds","created":"2025-12-28","cited_by_count":6},{"id":"2512.23133","title":"Principled Algorithms for Optimizing Generalized Metrics in Binary Classification","created":"2025-12-29","cited_by_count":6},{"id":"2601.22538","title":"Learning-to-Defer in Non-Stationary Time Series via Switching State-Space Models","created":"2026-01-30","cited_by_count":6},{"id":"2510.10988","title":"Adversarial Robustness in One-Stage Learning-to-Defer","created":"2025-10-13","cited_by_count":5},{"id":"2604.09414","title":"Beyond Augmented-Action Surrogates for Multi-Expert Learning-to-Defer","created":"2026-04-10","cited_by_count":5},{"id":"2602.17554","title":"A Theoretical Framework for Modular Learning of Robust Generative Models","created":"2026-02-19","cited_by_count":4}],"next_cursor":null}