{"list":"other","total":60,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2003.04297","title":"Improved Baselines with Momentum Contrastive Learning","created":"2020-03-09","cited_by_count":2287},{"id":"2103.03230","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","created":"2021-03-04","cited_by_count":1838},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1906.05849","title":"Contrastive Multiview Coding","created":"2019-06-13","cited_by_count":1301},{"id":"2105.04906","title":"VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning","created":"2021-05-11","cited_by_count":1057},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"1812.11118","title":"Reconciling modern machine learning practice and the bias-variance trade-off","created":"2018-12-28","cited_by_count":927},{"id":"1906.00910","title":"Learning Representations by Maximizing Mutual Information Across Views","created":"2019-06-03","cited_by_count":734},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"1906.11300","title":"Benign Overfitting in Linear Regression","created":"2019-06-26","cited_by_count":549},{"id":"1911.05371","title":"Self-labelling via simultaneous clustering and representation learning","created":"2019-11-13","cited_by_count":528},{"id":"2304.15004","title":"Are Emergent Abilities of Large Language Models a Mirage?","created":"2023-04-28","cited_by_count":523},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"1903.08560","title":"Surprises in High-Dimensional Ridgeless Least Squares Interpolation","created":"2019-03-19","cited_by_count":513},{"id":"1908.05355","title":"The generalization error of random features regression: Precise asymptotics and double descent curve","created":"2019-08-14","cited_by_count":413},{"id":"2305.16264","title":"Scaling Data-Constrained Language Models","created":"2023-05-25","cited_by_count":403},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2202.01169","title":"Unified Scaling Laws for Routed Language Models","created":"2022-02-02","cited_by_count":253},{"id":"1710.03667","title":"High-dimensional dynamics of generalization error in neural networks","created":"2017-10-10","cited_by_count":241},{"id":"1909.12673","title":"A Constructive Prediction of the Generalization Error Across Scales","created":"2019-09-27","cited_by_count":210},{"id":"1903.12355","title":"Local Aggregation for Unsupervised Learning of Visual Embeddings","created":"2019-03-29","cited_by_count":204},{"id":"1903.07571","title":"Two models of double descent for weak features","created":"2019-03-18","cited_by_count":195},{"id":"1808.00387","title":"Just Interpolate: Kernel \"Ridgeless\" Regression Can Generalize","created":"2018-08-01","cited_by_count":190},{"id":"2401.00448","title":"Beyond Chinchilla-Optimal: Accounting for Inference in Language Model Scaling Laws","created":"2023-12-31","cited_by_count":159},{"id":"2205.10487","title":"Scaling Laws and Interpretability of Learning from Repeated Data","created":"2022-05-21","cited_by_count":152},{"id":"2210.16859","title":"A Solvable Model of Neural Scaling Laws","created":"2022-10-30","cited_by_count":116},{"id":"2206.02574","title":"On the duality between contrastive and non-contrastive self-supervised learning","created":"2022-06-03","cited_by_count":108},{"id":"1704.05310","title":"Unsupervised Learning by Predicting Noise","created":"2017-04-18","cited_by_count":98},{"id":"2011.03321","title":"Understanding Double Descent Requires a Fine-Grained Bias-Variance Decomposition","created":"2020-11-04","cited_by_count":76},{"id":"2104.03113","title":"Scaling Scaling Laws with Board Games","created":"2021-04-07","cited_by_count":63},{"id":"1710.06487","title":"Classification and Geometry of General Perceptual Manifolds","created":"2017-10-17","cited_by_count":62},{"id":"2005.13149","title":"On Mutual Information in Contrastive Learning for Visual Representations","created":"2020-05-27","cited_by_count":54},{"id":"2303.01372","title":"High-dimensional analysis of double descent for linear regression with random projections","created":"2023-03-02","cited_by_count":47},{"id":"2406.04391","title":"Why Has Predicting Downstream Capabilities of Frontier AI Models with Scale Remained Elusive?","created":"2024-06-06","cited_by_count":40},{"id":"2210.00849","title":"Scaling Laws for a Multi-Agent Reinforcement Learning Model","created":"2022-09-29","cited_by_count":38},{"id":"2310.18988","title":"A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning","created":"2023-10-29","cited_by_count":33},{"id":"2303.03307","title":"Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations","created":"2023-03-06","cited_by_count":31},{"id":"2103.11275","title":"Self-supervised Representation Learning with Relative Predictive Coding","created":"2021-03-21","cited_by_count":28},{"id":"2010.13933","title":"Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized models","created":"2020-10-26","cited_by_count":27},{"id":"2303.00633","title":"An Information-Theoretic Perspective on Variance-Invariance-Covariance Regularization","created":"2023-03-01","cited_by_count":25},{"id":"1912.06190","title":"Double descent in the condition number","created":"2019-12-12","cited_by_count":14},{"id":"2307.10907","title":"The Role of Entropy and Reconstruction in Multi-View Self-Supervised Learning","created":"2023-07-20","cited_by_count":13},{"id":"2206.10698","title":"TiCo: Transformation Invariance and Covariance Contrast for Self-Supervised Visual Representation Learning","created":"2022-06-21","cited_by_count":12},{"id":"2203.05443","title":"Bias-variance decomposition of overparameterized regression with random linear features","created":"2022-03-10","cited_by_count":7},{"id":"2103.14108","title":"The Geometry of Over-parameterized Regression and Adversarial Perturbations","created":"2021-03-25","cited_by_count":4},{"id":"2307.07872","title":"Does Double Descent Occur in Self-Supervised Learning?","created":"2023-07-15","cited_by_count":3}],"next_cursor":null}