{"list":"other","total":57,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1509.01626","title":"Character-level Convolutional Networks for Text Classification","created":"2015-09-04","cited_by_count":2330},{"id":"1910.03771","title":"HuggingFace's Transformers: State-of-the-art Natural Language Processing","created":"2019-10-09","cited_by_count":2218},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"1804.06872","title":"Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels","created":"2018-04-18","cited_by_count":1059},{"id":"1805.07836","title":"Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labels","created":"2018-05-20","cited_by_count":997},{"id":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"1706.05394","title":"A Closer Look at Memorization in Deep Networks","created":"2017-06-16","cited_by_count":942},{"id":"1802.03268","title":"Efficient Neural Architecture Search via Parameter Sharing","created":"2018-02-09","cited_by_count":837},{"id":"1803.09050","title":"Learning to Reweight Examples for Robust Deep Learning","created":"2018-03-24","cited_by_count":675},{"id":"1712.05055","title":"MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels","created":"2017-12-14","cited_by_count":653},{"id":"2102.07350","title":"Prompt Programming for Large Language Models: Beyond the Few-Shot Paradigm","created":"2021-02-15","cited_by_count":606},{"id":"2006.05929","title":"Dataset Condensation with Gradient Matching","created":"2020-06-10","cited_by_count":516},{"id":"1908.06112","title":"Symmetric Cross Entropy for Robust Learning with Noisy Labels","created":"2019-08-16","cited_by_count":500},{"id":"1712.09482","title":"Robust Loss Functions under Label Noise for Deep Neural Networks","created":"2017-12-27","cited_by_count":443},{"id":"2203.11932","title":"Dataset Distillation by Matching Training Trajectories","created":"2022-03-22","cited_by_count":442},{"id":"2009.10795","title":"Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics","created":"2020-09-22","cited_by_count":425},{"id":"1901.04215","title":"How does Disagreement Help Generalization against Label Corruption?","created":"2019-01-14","cited_by_count":390},{"id":"1901.09960","title":"Using Pre-Training Can Improve Model Robustness and Uncertainty","created":"2019-01-28","cited_by_count":373},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1412.6596","title":"Training Deep Neural Networks on Noisy Labels with Bootstrapping","created":"2014-12-20","cited_by_count":322},{"id":"1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","created":"2019-11-06","cited_by_count":304},{"id":"2006.13554","title":"Normalized Loss Functions for Deep Learning with Noisy Labels","created":"2020-06-24","cited_by_count":257},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"2202.07922","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","created":"2022-02-16","cited_by_count":211},{"id":"2201.05955","title":"WANLI: Worker and AI Collaboration for Natural Language Inference Dataset Creation","created":"2022-01-16","cited_by_count":202},{"id":"2202.04538","title":"Generating Training Data with Language Models: Towards Zero-Shot Language Understanding","created":"2022-02-09","cited_by_count":199},{"id":"2108.13487","title":"Want To Reduce Labeling Cost? GPT-3 Can Help","created":"2021-08-30","cited_by_count":196},{"id":"2104.07540","title":"Generating Datasets with Pretrained Language Models","created":"2021-04-15","cited_by_count":193},{"id":"1810.10667","title":"Truncated Back-propagation for Bilevel Optimization","created":"2018-10-25","cited_by_count":190},{"id":"2104.08826","title":"GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation","created":"2021-04-18","cited_by_count":187},{"id":"1911.03118","title":"Not Enough Data? Deep Learning to the Rescue!","created":"2019-11-08","cited_by_count":175},{"id":"1806.02612","title":"Dimensionality-Driven Learning with Noisy Labels","created":"2018-06-07","cited_by_count":173},{"id":"2003.02245","title":"Data Augmentation using Pre-trained Transformer Models","created":"2020-03-04","cited_by_count":168},{"id":"2010.02347","title":"Learning with Instance-Dependent Label Noise: A Sample Sieve Approach","created":"2020-10-05","cited_by_count":158},{"id":"1910.03231","title":"Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Rates","created":"2019-10-08","cited_by_count":142},{"id":"1705.06270","title":"A Review on Bilevel Optimization: From Classical to Evolutionary Approaches and Applications","created":"2017-05-17","cited_by_count":129},{"id":"1911.03809","title":"Meta Label Correction for Noisy Label Learning","created":"2019-11-10","cited_by_count":108},{"id":"1903.03088","title":"Self-Tuning Networks: Bilevel Optimization of Hyperparameters using Structured Best-Response Functions","created":"2019-03-07","cited_by_count":105},{"id":"2002.09599","title":"Training Question Answering Models From Synthetic Data","created":"2020-02-22","cited_by_count":95},{"id":"1905.10964","title":"Combating Label Noise in Deep Learning Using Abstention","created":"2019-05-27","cited_by_count":86},{"id":"1605.06423","title":"Coresets for Scalable Bayesian Logistic Regression","created":"2016-05-20","cited_by_count":79},{"id":"2109.09193","title":"Towards Zero-Label Language Learning","created":"2021-09-19","cited_by_count":76},{"id":"2102.01335","title":"Neural Data Augmentation via Example Extrapolation","created":"2021-02-02","cited_by_count":54},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"2102.12871","title":"SparseBERT: Rethinking the Importance Analysis in Self-attention","created":"2021-02-25","cited_by_count":46},{"id":"1703.08110","title":"Training Gaussian Mixture Models at Scale via Coresets","created":"2017-03-23","cited_by_count":38},{"id":"1901.10310","title":"Robust Learning from Untrusted Sources","created":"2019-01-29","cited_by_count":27},{"id":"2105.12971","title":"Joint-DetNAS: Upgrade Your Detector with NAS, Pruning and Dynamic Distillation","created":"2021-05-27","cited_by_count":23},{"id":"2107.07445","title":"AutoBERT-Zero: Evolving BERT Backbone from Scratch","created":"2021-07-15","cited_by_count":21},{"id":"2010.01288","title":"UNISON: Unpaired Cross-lingual Image Captioning","created":"2020-10-03","cited_by_count":8}],"next_cursor":null}