{"list":"other","total":64,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1602.05629","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","created":"2016-02-17","cited_by_count":7669},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1912.04977","title":"Advances and Open Problems in Federated Learning","created":"2019-12-10","cited_by_count":3046},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"1607.00133","title":"Deep Learning with Differential Privacy","created":"2016-07-01","cited_by_count":2728},{"id":"1901.08746","title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","created":"2019-01-25","cited_by_count":1947},{"id":"1703.04730","title":"Understanding Black-box Predictions via Influence Functions","created":"2017-03-14","cited_by_count":1741},{"id":"2004.10964","title":"Don't Stop Pretraining: Adapt Language Models to Domains and Tasks","created":"2020-04-23","cited_by_count":1565},{"id":"1908.07873","title":"Federated Learning: Challenges, Methods, and Future Directions","created":"2019-08-21","cited_by_count":1538},{"id":"1904.08779","title":"SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition","created":"2019-04-18","cited_by_count":1380},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"1906.08935","title":"Deep Leakage from Gradients","created":"2019-06-21","cited_by_count":1021},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"1707.02968","title":"Revisiting Unreasonable Effectiveness of Data in Deep Learning Era","created":"2017-07-10","cited_by_count":919},{"id":"1902.01046","title":"Towards Federated Learning at Scale: System Design","created":"2019-02-04","cited_by_count":832},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"2103.03097","title":"Generalizing to Unseen Domains: A Survey on Domain Generalization","created":"2021-03-02","cited_by_count":766},{"id":"1807.00459","title":"How To Backdoor Federated Learning","created":"2018-07-02","cited_by_count":765},{"id":"2003.14053","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","created":"2020-03-31","cited_by_count":712},{"id":"1907.00503","title":"Modeling Tabular data using Conditional GAN","created":"2019-07-01","cited_by_count":699},{"id":"2006.09359","title":"AWAC: Accelerating Online Reinforcement Learning with Offline Datasets","created":"2020-06-16","cited_by_count":671},{"id":"2003.08119","title":"The Future of Digital Health with Federated Learning","created":"2020-03-18","cited_by_count":633},{"id":"1904.02868","title":"Data Shapley: Equitable Valuation of Data for Machine Learning","created":"2019-04-05","cited_by_count":629},{"id":"1805.00932","title":"Exploring the Limits of Weakly Supervised Pretraining","created":"2018-05-02","cited_by_count":605},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2008.03703","title":"What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation","created":"2020-08-09","cited_by_count":497},{"id":"2104.08758","title":"Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus","created":"2021-04-18","cited_by_count":492},{"id":"1712.07557","title":"Differentially Private Federated Learning: A Client Level Perspective","created":"2017-12-20","cited_by_count":459},{"id":"2007.00644","title":"Measuring Robustness to Natural Distribution Shifts in Image Classification","created":"2020-07-01","cited_by_count":454},{"id":"2108.04884","title":"Retiring Adult: New Datasets for Fair Machine Learning","created":"2021-08-10","cited_by_count":449},{"id":"2406.11794","title":"DataComp-LM: In search of the next generation of training sets for language models","created":"2024-06-17","cited_by_count":398},{"id":"1902.10275","title":"Towards Efficient Data Valuation Based on the Shapley Value","created":"2019-02-27","cited_by_count":281},{"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":"2011.11660","title":"Differentially Private Learning Needs Better Features (or Much More Data)","created":"2020-11-23","cited_by_count":235},{"id":"1812.03224","title":"A Hybrid Approach to Privacy-Preserving Federated Learning","created":"2018-12-07","cited_by_count":210},{"id":"2202.00622","title":"Datamodels: Predicting Predictions from Training Data","created":"2022-02-01","cited_by_count":189},{"id":"2010.10504","title":"Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition","created":"2020-10-20","cited_by_count":187},{"id":"2111.08834","title":"Federated Learning for Smart Healthcare: A Survey","created":"2021-11-16","cited_by_count":184},{"id":"2309.09400","title":"CulturaX: A Cleaned, Enormous, and Multilingual Dataset for Large Language Models in 167 Languages","created":"2023-09-17","cited_by_count":174},{"id":"2012.06337","title":"Privacy and Robustness in Federated Learning: Attacks and Defenses","created":"2020-12-07","cited_by_count":166},{"id":"1805.12002","title":"Why Is My Classifier Discriminatory?","created":"2018-05-30","cited_by_count":143},{"id":"2109.00984","title":"CrypTen: Secure Multi-Party Computation Meets Machine Learning","created":"2021-09-02","cited_by_count":131},{"id":"2112.02918","title":"When the Curious Abandon Honesty: Federated Learning Is Not Private","created":"2021-12-06","cited_by_count":127},{"id":"2007.14191","title":"Tempered Sigmoid Activations for Deep Learning with Differential Privacy","created":"2020-07-28","cited_by_count":122},{"id":"2104.14380","title":"PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments","created":"2021-04-29","cited_by_count":93},{"id":"2210.15424","title":"What Language Model to Train if You Have One Million GPU Hours?","created":"2022-10-27","cited_by_count":92},{"id":"2309.10818","title":"SlimPajama-DC: Understanding Data Combinations for LLM Training","created":"2023-09-19","cited_by_count":72},{"id":"2305.18465","title":"Federated Learning of Gboard Language Models with Differential Privacy","created":"2023-05-29","cited_by_count":66},{"id":"2310.05077","title":"FedFed: Feature Distillation against Data Heterogeneity in Federated Learning","created":"2023-10-08","cited_by_count":54},{"id":"2108.09749","title":"Flexible Clustered Federated Learning for Client-Level Data Distribution Shift","created":"2021-08-22","cited_by_count":47},{"id":"2107.00471","title":"SinGAN-Seg: Synthetic training data generation for medical image segmentation","created":"2021-06-29","cited_by_count":43},{"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":"2409.04556","title":"How Does Code Pretraining Affect Language Model Task Performance?","created":"2024-09-06","cited_by_count":28},{"id":"2108.03437","title":"Secure Neuroimaging Analysis using Federated Learning with Homomorphic Encryption","created":"2021-08-07","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":"1710.08874","title":"Synthetic Data for Social Good","created":"2017-10-24","cited_by_count":15},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15},{"id":"2003.01593","title":"Marketplace for AI Models","created":"2020-03-03","cited_by_count":6},{"id":"2411.03351","title":"Tabular Data Synthesis with Differential Privacy: A Survey","created":"2024-11-04","cited_by_count":6},{"id":"2305.02942","title":"Incentivising the federation: gradient-based metrics for data selection and valuation in private decentralised training","created":"2023-05-04","cited_by_count":3},{"id":"2012.06430","title":"Data Appraisal Without Data Sharing","created":"2020-12-11","cited_by_count":2},{"id":"2402.13700","title":"On the Conflict of Robustness and Learning in Collaborative Machine Learning","created":"2024-02-21","cited_by_count":1}],"next_cursor":null}