{"list":"other","total":56,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1806.07572","title":"Neural Tangent Kernel: Convergence and Generalization in Neural Networks","created":"2018-06-20","cited_by_count":2621},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"2012.13255","title":"Intrinsic Dimensionality Explains the Effectiveness of Language Model Fine-Tuning","created":"2020-12-22","cited_by_count":671},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1805.04770","title":"Born Again Neural Networks","created":"2018-05-12","cited_by_count":546},{"id":"2402.04333","title":"LESS: Selecting Influential Data for Targeted Instruction Tuning","created":"2024-02-06","cited_by_count":532},{"id":"1905.08094","title":"Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation","created":"2019-05-17","cited_by_count":497},{"id":"2312.09390","title":"Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision","created":"2023-12-14","cited_by_count":467},{"id":"1812.01187","title":"Bag of Tricks for Image Classification with Convolutional Neural Networks","created":"2018-12-04","cited_by_count":431},{"id":"1702.08423","title":"Age Progression/Regression by Conditional Adversarial Autoencoder","created":"2017-02-27","cited_by_count":429},{"id":"1804.08838","title":"Measuring the Intrinsic Dimension of Objective Landscapes","created":"2018-04-24","cited_by_count":370},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"2002.09277","title":"Kernel and Rich Regimes in Overparametrized Models","created":"2020-02-20","cited_by_count":306},{"id":"1411.4357","title":"Sketching as a Tool for Numerical Linear Algebra","created":"2014-11-17","cited_by_count":288},{"id":"2106.05945","title":"Does Knowledge Distillation Really Work?","created":"2021-06-10","cited_by_count":190},{"id":"2010.03622","title":"Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Data","created":"2020-10-07","cited_by_count":180},{"id":"2002.05715","title":"Self-Distillation Amplifies Regularization in Hilbert Space","created":"2020-02-13","cited_by_count":173},{"id":"2105.13093","title":"Towards Understanding Knowledge Distillation","created":"2021-05-27","cited_by_count":158},{"id":"2402.00530","title":"Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning","created":"2024-02-01","cited_by_count":138},{"id":"2210.05643","title":"A Kernel-Based View of Language Model Fine-Tuning","created":"2022-10-11","cited_by_count":121},{"id":"2002.11328","title":"Rethinking Bias-Variance Trade-off for Generalization of Neural Networks","created":"2020-02-26","cited_by_count":107},{"id":"2111.00743","title":"Towards the Generalization of Contrastive Self-Supervised Learning","created":"2021-11-01","cited_by_count":99},{"id":"2005.08054","title":"Classification vs regression in overparameterized regimes: Does the loss function matter?","created":"2020-05-16","cited_by_count":97},{"id":"2403.09472","title":"Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision","created":"2024-03-14","cited_by_count":96},{"id":"2203.06176","title":"More Than a Toy: Random Matrix Models Predict How Real-World Neural Representations Generalize","created":"2022-03-11","cited_by_count":91},{"id":"2204.00570","title":"Connect, Not Collapse: Explaining Contrastive Learning for Unsupervised Domain Adaptation","created":"2022-04-01","cited_by_count":67},{"id":"2502.04313","title":"Great Models Think Alike and this Undermines AI Oversight","created":"2025-02-06","cited_by_count":58},{"id":"2102.11203","title":"A Theory of Label Propagation for Subpopulation Shift","created":"2021-02-22","cited_by_count":48},{"id":"2405.16043","title":"Theoretical Analysis of Weak-to-Strong Generalization","created":"2024-05-25","cited_by_count":48},{"id":"2405.15116","title":"Quantifying the Gain in Weak-to-Strong Generalization","created":"2024-05-24","cited_by_count":41},{"id":"1912.10754","title":"Exact minimax risk for linear least squares, and the lower tail of sample covariance matrices","created":"2019-12-23","cited_by_count":34},{"id":"2407.13647","title":"Weak-to-Strong Reasoning","created":"2024-07-18","cited_by_count":33},{"id":"2006.10732","title":"When Does Preconditioning Help or Hurt Generalization?","created":"2020-06-18","cited_by_count":31},{"id":"2202.12230","title":"Sample Efficiency of Data Augmentation Consistency Regularization","created":"2022-02-24","cited_by_count":28},{"id":"2402.03749","title":"Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Models","created":"2024-02-06","cited_by_count":28},{"id":"2402.15505","title":"Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Experts","created":"2024-02-23","cited_by_count":28},{"id":"2205.16004","title":"What Knowledge Gets Distilled in Knowledge Distillation?","created":"2022-05-31","cited_by_count":27},{"id":"2406.11431","title":"Super(ficial)-alignment: Strong Models May Deceive Weak Models in Weak-to-Strong Generalization","created":"2024-06-17","cited_by_count":23},{"id":"2410.18837","title":"High-dimensional Analysis of Knowledge Distillation: Weak-to-Strong Generalization and Scaling Laws","created":"2024-10-24","cited_by_count":22},{"id":"2301.13304","title":"Understanding Self-Distillation in the Presence of Label Noise","created":"2023-01-30","cited_by_count":21},{"id":"2412.03881","title":"Weak-to-Strong Generalization Through the Data-Centric Lens","created":"2024-12-05","cited_by_count":21},{"id":"2106.13805","title":"Self-training Converts Weak Learners to Strong Learners in Mixture Models","created":"2021-06-25","cited_by_count":19},{"id":"2301.12923","title":"On student-teacher deviations in distillation: does it pay to disobey?","created":"2023-01-30","cited_by_count":16},{"id":"2410.04638","title":"Provable Weak-to-Strong Generalization via Benign Overfitting","created":"2024-10-06","cited_by_count":16},{"id":"2407.04600","title":"Understanding the Gains from Repeated Self-Distillation","created":"2024-07-05","cited_by_count":15},{"id":"2406.19032","title":"Improving Weak-to-Strong Generalization with Reliability-Aware Alignment","created":"2024-06-27","cited_by_count":14},{"id":"2502.00620","title":"Representations Shape Weak-to-Strong Generalization: Theoretical Insights and Empirical Predictions","created":"2025-02-02","cited_by_count":10},{"id":"2307.11030","title":"Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering","created":"2023-07-20","cited_by_count":7},{"id":"2407.06120","title":"Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning","created":"2024-07-08","cited_by_count":5},{"id":"2210.01891","title":"Adaptively Weighted Data Augmentation Consistency Regularization for Robust Optimization under Concept Shift","created":"2022-10-04","cited_by_count":3},{"id":"2304.02641","title":"Self-Distillation for Gaussian Process Regression and Classification","created":"2023-04-05","cited_by_count":1}],"next_cursor":null}