{"list":"other","total":53,"rows":[{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2103.03874","title":"Measuring Mathematical Problem Solving With the MATH Dataset","created":"2021-03-05","cited_by_count":5371},{"id":"1804.07461","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","created":"2018-04-20","cited_by_count":4899},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"1706.03741","title":"Deep reinforcement learning from human preferences","created":"2017-06-12","cited_by_count":3912},{"id":"2101.00027","title":"The Pile: An 800GB Dataset of Diverse Text for Language Modeling","created":"2020-12-31","cited_by_count":2411},{"id":"2304.01373","title":"Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling","created":"2023-04-03","cited_by_count":1786},{"id":"1610.01644","title":"Understanding intermediate layers using linear classifier probes","created":"2016-10-05","cited_by_count":1353},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"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":"1902.09229","title":"A Theoretical Analysis of Contrastive Unsupervised Representation Learning","created":"2019-02-25","cited_by_count":530},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"2008.01064","title":"Predicting What You Already Know Helps: Provable Self-Supervised Learning","created":"2020-08-03","cited_by_count":152},{"id":"2006.13409","title":"When Do Neural Networks Outperform Kernel Methods?","created":"2020-06-24","cited_by_count":150},{"id":"2205.01445","title":"High-dimensional Asymptotics of Feature Learning: How One Gradient Step Improves the Representation","created":"2022-05-03","cited_by_count":150},{"id":"1507.03003","title":"High-Dimensional Asymptotics of Prediction: Ridge Regression and Classification","created":"2015-07-10","cited_by_count":148},{"id":"2302.00294","title":"The geometry of hidden representations of large transformer models","created":"2023-02-01","cited_by_count":112},{"id":"2006.05800","title":"On the Optimal Weighted $\\ell_2$ Regularization in Overparameterized Linear Regression","created":"2020-06-10","cited_by_count":98},{"id":"2411.07279","title":"The Surprising Effectiveness of Test-Time Training for Few-Shot Learning","created":"2024-11-11","cited_by_count":96},{"id":"1809.10374","title":"An analytic theory of generalization dynamics and transfer learning in deep linear networks","created":"2018-09-27","cited_by_count":85},{"id":"2006.06386","title":"Asymptotics of Ridge (less) Regression under General Source Condition","created":"2020-06-11","cited_by_count":62},{"id":"1909.12362","title":"Overparameterized Neural Networks Implement Associative Memory","created":"2019-09-26","cited_by_count":45},{"id":"2201.07311","title":"Datasheet for the Pile","created":"2022-01-13","cited_by_count":43},{"id":"1804.10253","title":"From Principal Subspaces to Principal Components with Linear Autoencoders","created":"2018-04-26","cited_by_count":39},{"id":"2402.04980","title":"Asymptotics of feature learning in two-layer networks after one gradient-step","created":"2024-02-07","cited_by_count":38},{"id":"2309.03843","title":"Gradient-Based Feature Learning under Structured Data","created":"2023-09-07","cited_by_count":32},{"id":"2010.11750","title":"Precise High-Dimensional Asymptotics for Quantifying Heterogeneous Transfers","created":"2020-10-22","cited_by_count":27},{"id":"2201.02115","title":"The dynamics of representation learning in shallow, non-linear autoencoders","created":"2022-01-06","cited_by_count":27},{"id":"2309.14563","title":"Towards a statistical theory of data selection under weak supervision","created":"2023-09-25","cited_by_count":27},{"id":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27},{"id":"2106.05418","title":"Probing transfer learning with a model of synthetic correlated datasets","created":"2021-06-09","cited_by_count":25},{"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":"2104.05694","title":"On the Inductive Bias of Masked Language Modeling: From Statistical to Syntactic Dependencies","created":"2021-04-12","cited_by_count":18},{"id":"2406.13944","title":"Generalization error of min-norm interpolators in transfer learning","created":"2024-06-20","cited_by_count":16},{"id":"2410.18938","title":"A Random Matrix Theory Perspective on the Spectrum of Learned Features and Asymptotic Generalization Capabilities","created":"2024-10-24","cited_by_count":16},{"id":"2410.08194","title":"Features are fate: a theory of transfer learning in high-dimensional regression","created":"2024-10-10","cited_by_count":13},{"id":"2006.16540","title":"Associative Memory in Iterated Overparameterized Sigmoid Autoencoders","created":"2020-06-30","cited_by_count":9},{"id":"2502.01347","title":"Spurious Correlations in High Dimensional Regression: The Roles of Regularization, Simplicity Bias and Over-Parameterization","created":"2025-02-03","cited_by_count":9},{"id":"2505.22785","title":"Navigating the Latent Space Dynamics of Neural Models","created":"2025-05-28","cited_by_count":8},{"id":"2510.08123","title":"High-dimensional Analysis of Synthetic Data Selection","created":"2025-10-09","cited_by_count":7},{"id":"2502.16849","title":"Provable Benefits of Unsupervised Pre-training and Transfer Learning via Single-Index Models","created":"2025-02-24","cited_by_count":6},{"id":"2602.20062","title":"A Theory of How Pretraining Shapes Inductive Bias in Fine-Tuning","created":"2026-02-23","cited_by_count":5},{"id":"1709.10045","title":"Effective learning is accompanied by high dimensional and efficient representations of neural activity","created":"2017-09-28","cited_by_count":4},{"id":"2510.01303","title":"Low Rank Gradients and Where to Find Them","created":"2025-10-01","cited_by_count":4},{"id":"2510.09816","title":"A mathematical theory for understanding when abstract representations emerge in neural networks","created":"2025-10-10","cited_by_count":4},{"id":"2409.03335","title":"Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data","created":"2024-09-05","cited_by_count":3},{"id":"2510.12249","title":"Optimal Regularization for Performative Learning","created":"2025-10-14","cited_by_count":1}],"next_cursor":null}