{"list":"other","total":58,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"1911.02685","title":"A Comprehensive Survey on Transfer Learning","created":"2019-11-07","cited_by_count":1160},{"id":"2007.01434","title":"In Search of Lost Domain Generalization","created":"2020-07-02","cited_by_count":1054},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2108.10904","title":"SimVLM: Simple Visual Language Model Pretraining with Weak Supervision","created":"2021-08-24","cited_by_count":647},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"id":"2206.14486","title":"Beyond neural scaling laws: beating power law scaling via data pruning","created":"2022-06-29","cited_by_count":528},{"id":"1906.05271","title":"Does Learning Require Memorization? A Short Tale about a Long Tail","created":"2019-06-12","cited_by_count":460},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"id":"1905.13736","title":"Unlabeled Data Improves Adversarial Robustness","created":"2019-05-31","cited_by_count":416},{"id":"2305.10429","title":"DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining","created":"2023-05-17","cited_by_count":399},{"id":"2102.06701","title":"Explaining Neural Scaling Laws","created":"2021-02-12","cited_by_count":363},{"id":"1812.02849","title":"A Survey of Unsupervised Deep Domain Adaptation","created":"2018-12-06","cited_by_count":361},{"id":"1904.05801","title":"Bridging Theory and Algorithm for Domain Adaptation","created":"2019-04-11","cited_by_count":332},{"id":"1709.10190","title":"Unified Deep Supervised Domain Adaptation and Generalization","created":"2017-09-28","cited_by_count":323},{"id":"2012.05345","title":"Data and its (dis)contents: A survey of dataset development and use in machine learning research","created":"2020-12-09","cited_by_count":260},{"id":"2107.04649","title":"Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization","created":"2021-07-09","cited_by_count":249},{"id":"2110.11328","title":"A Fine-Grained Analysis on Distribution Shift","created":"2021-10-21","cited_by_count":171},{"id":"2010.03058","title":"Characterising Bias in Compressed Models","created":"2020-10-06","cited_by_count":167},{"id":"2003.00827","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","created":"2020-02-14","cited_by_count":153},{"id":"1805.12002","title":"Why Is My Classifier Discriminatory?","created":"2018-05-30","cited_by_count":143},{"id":"2111.08006","title":"Disparities in Dermatology AI: Assessments Using Diverse Clinical Images","created":"2021-11-15","cited_by_count":134},{"id":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120},{"id":"1909.11512","title":"Synthetic Data for Deep Learning","created":"2019-09-25","cited_by_count":113},{"id":"1812.11806","title":"An introduction to domain adaptation and transfer learning","created":"2018-12-31","cited_by_count":112},{"id":"2006.12204","title":"Telescoping Density-Ratio Estimation","created":"2020-06-22","cited_by_count":108},{"id":"2011.04946","title":"When Do You Need Billions of Words of Pretraining Data?","created":"2020-11-10","cited_by_count":104},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97},{"id":"2103.10948","title":"The Shape of Learning Curves: a Review","created":"2021-03-19","cited_by_count":70},{"id":"2111.11010","title":"Density Ratio Estimation via Infinitesimal Classification","created":"2021-11-22","cited_by_count":61},{"id":"2202.01994","title":"Data Scaling Laws in NMT: The Effect of Noise and Architecture","created":"2022-02-04","cited_by_count":55},{"id":"2106.11344","title":"f-Domain-Adversarial Learning: Theory and Algorithms","created":"2021-06-21","cited_by_count":47},{"id":"2202.01034","title":"Diagnosing failures of fairness transfer across distribution shift in real-world medical settings","created":"2022-02-02","cited_by_count":45},{"id":"1902.05826","title":"The Fairness of Risk Scores Beyond Classification: Bipartite Ranking and the xAUC Metric","created":"2019-02-15","cited_by_count":41},{"id":"1908.00690","title":"Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks","created":"2019-08-02","cited_by_count":39},{"id":"2303.02011","title":"Diagnosing Model Performance Under Distribution Shift","created":"2023-03-03","cited_by_count":39},{"id":"2103.03399","title":"Representation Matters: Assessing the Importance of Subgroup Allocations in Training Data","created":"2021-03-05","cited_by_count":31},{"id":"2306.05109","title":"Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML","created":"2023-06-08","cited_by_count":29},{"id":"2209.09125","title":"Operationalizing Machine Learning: An Interview Study","created":"2022-09-16","cited_by_count":25},{"id":"2205.11672","title":"Why does Throwing Away Data Improve Worst-Group Error?","created":"2022-05-23","cited_by_count":22},{"id":"2210.10769","title":"\"Why did the Model Fail?\": Attributing Model Performance Changes to Distribution Shifts","created":"2022-10-19","cited_by_count":18},{"id":"2212.05129","title":"Measuring Data","created":"2022-12-09","cited_by_count":18},{"id":"2308.04431","title":"When More is Less: Incorporating Additional Datasets Can Hurt Performance By Introducing Spurious Correlations","created":"2023-08-08","cited_by_count":18},{"id":"2003.04549","title":"Slice Tuner: A Selective Data Acquisition Framework for Accurate and Fair Machine Learning Models","created":"2020-03-10","cited_by_count":13},{"id":"2102.07005","title":"Clustering Interval-Censored Time-Series for Disease Phenotyping","created":"2021-02-13","cited_by_count":11},{"id":"2305.00195","title":"Data-Driven Subgroup Identification for Linear Regression","created":"2023-04-29","cited_by_count":6},{"id":"2009.09084","title":"Intimate Partner Violence and Injury Prediction From Radiology Reports","created":"2020-08-28","cited_by_count":4},{"id":"2402.03597","title":"Identifying Reasons for Contraceptive Switching from Real-World Data Using Large Language Models","created":"2024-02-06","cited_by_count":4},{"id":"2205.01157","title":"Leximax Approximations and Representative Cohort Selection","created":"2022-05-02","cited_by_count":3},{"id":"2205.13398","title":"Looking for Out-of-Distribution Environments in Multi-center Critical Care Data","created":"2022-05-26","cited_by_count":3},{"id":"2405.00614","title":"Multigroup Robustness","created":"2024-05-01","cited_by_count":2}],"next_cursor":null}