{"list":"other","total":116,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1406.1078","title":"Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation","created":"2014-06-03","cited_by_count":4057},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"1506.02626","title":"Learning both Weights and Connections for Efficient Neural Networks","created":"2015-06-08","cited_by_count":2031},{"id":"1607.00653","title":"node2vec: Scalable Feature Learning for Networks","created":"2016-07-03","cited_by_count":1918},{"id":"1909.08053","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","created":"2019-09-17","cited_by_count":1868},{"id":"1806.09055","title":"DARTS: Differentiable Architecture Search","created":"2018-06-24","cited_by_count":1798},{"id":"1703.06103","title":"Modeling Relational Data with Graph Convolutional Networks","created":"2017-03-17","cited_by_count":1694},{"id":"2006.05525","title":"Knowledge Distillation: A Survey","created":"2020-06-09","cited_by_count":1603},{"id":"1611.01578","title":"Neural Architecture Search with Reinforcement Learning","created":"2016-11-05","cited_by_count":1499},{"id":"1803.01271","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","created":"2018-03-04","cited_by_count":1476},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1707.07012","title":"Learning Transferable Architectures for Scalable Image Recognition","created":"2017-07-21","cited_by_count":1101},{"id":"1802.01548","title":"Regularized Evolution for Image Classifier Architecture Search","created":"2018-02-05","cited_by_count":909},{"id":"1606.06357","title":"Complex Embeddings for Simple Link Prediction","created":"2016-06-20","cited_by_count":902},{"id":"1902.10197","title":"RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space","created":"2019-02-26","cited_by_count":898},{"id":"1707.01476","title":"Convolutional 2D Knowledge Graph Embeddings","created":"2017-07-05","cited_by_count":730},{"id":"1812.00332","title":"ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware","created":"2018-12-02","cited_by_count":673},{"id":"2002.00388","title":"A Survey on Knowledge Graphs: Representation, Acquisition and Applications","created":"2020-02-02","cited_by_count":643},{"id":"2201.11990","title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","created":"2022-01-28","cited_by_count":559},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511},{"id":"1712.00559","title":"Progressive Neural Architecture Search","created":"2017-12-02","cited_by_count":487},{"id":"1807.01774","title":"BOHB: Robust and Efficient Hyperparameter Optimization at Scale","created":"2018-07-04","cited_by_count":470},{"id":"2108.13624","title":"Towards Out-Of-Distribution Generalization: A Survey","created":"2021-08-31","cited_by_count":436},{"id":"1908.00709","title":"AutoML: A Survey of the State-of-the-Art","created":"2019-08-02","cited_by_count":390},{"id":"1907.09693","title":"A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection","created":"2019-07-23","cited_by_count":374},{"id":"1801.01489","title":"All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously","created":"2018-01-04","cited_by_count":373},{"id":"1502.03492","title":"Gradient-based Hyperparameter Optimization through Reversible Learning","created":"2015-02-11","cited_by_count":360},{"id":"1703.01041","title":"Large-Scale Evolution of Image Classifiers","created":"2017-03-03","cited_by_count":348},{"id":"1810.11921","title":"AutoInt: Automatic Feature Interaction Learning via Self-Attentive Neural Networks","created":"2018-10-29","cited_by_count":320},{"id":"1901.04592","title":"Interpretable machine learning: definitions, methods, and applications","created":"2019-01-14","cited_by_count":305},{"id":"2111.09266","title":"GFlowNet Foundations","created":"2021-11-17","cited_by_count":290},{"id":"1911.13288","title":"Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019","created":"2019-11-29","cited_by_count":273},{"id":"1902.07638","title":"Random Search and Reproducibility for Neural Architecture Search","created":"2019-02-20","cited_by_count":254},{"id":"1703.01785","title":"Forward and Reverse Gradient-Based Hyperparameter Optimization","created":"2017-03-06","cited_by_count":234},{"id":"1606.05386","title":"Model-Agnostic Interpretability of Machine Learning","created":"2016-06-16","cited_by_count":219},{"id":"2107.14351","title":"Contemporary Symbolic Regression Methods and their Relative Performance","created":"2021-07-29","cited_by_count":215},{"id":"1612.08468","title":"Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models","created":"2016-12-27","cited_by_count":213},{"id":"1908.11775","title":"Transformer Dissection: A Unified Understanding of Transformer's Attention via the Lens of Kernel","created":"2019-08-30","cited_by_count":213},{"id":"1802.02871","title":"Online Learning: A Comprehensive Survey","created":"2018-02-08","cited_by_count":205},{"id":"2002.02770","title":"A Survey on Causal Inference","created":"2020-02-05","cited_by_count":202},{"id":"1802.07191","title":"Neural Architecture Search with Bayesian Optimisation and Optimal Transport","created":"2018-02-11","cited_by_count":195},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"2106.06427","title":"Neural Symbolic Regression that Scales","created":"2021-06-11","cited_by_count":192},{"id":"1910.11858","title":"BANANAS: Bayesian Optimization with Neural Architectures for Neural Architecture Search","created":"2019-10-25","cited_by_count":179},{"id":"1906.04928","title":"Deep Learning for Spatio-Temporal Data Mining: A Survey","created":"2019-06-11","cited_by_count":172},{"id":"1806.10282","title":"Auto-Keras: An Efficient Neural Architecture Search System","created":"2018-06-27","cited_by_count":171},{"id":"1601.00770","title":"End-to-End Relation Extraction using LSTMs on Sequences and Tree Structures","created":"2016-01-05","cited_by_count":161},{"id":"1705.11040","title":"End-to-End Differentiable Proving","created":"2017-05-31","cited_by_count":161},{"id":"1704.03578","title":"A Survey on Homomorphic Encryption Schemes: Theory and Implementation","created":"2017-04-12","cited_by_count":156},{"id":"1804.09081","title":"Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution","created":"2018-04-24","cited_by_count":153},{"id":"1809.10185","title":"Graph Convolution over Pruned Dependency Trees Improves Relation Extraction","created":"2018-09-26","cited_by_count":146},{"id":"1605.07079","title":"Fast Bayesian Optimization of Machine Learning Hyperparameters on Large Datasets","created":"2016-05-23","cited_by_count":132},{"id":"1703.01513","title":"Genetic CNN","created":"2017-03-04","cited_by_count":124},{"id":"1910.11470","title":"A Survey on Recent Advances in Named Entity Recognition from Deep Learning models","created":"2019-10-25","cited_by_count":117},{"id":"1610.02995","title":"Extrapolation and learning equations","created":"2016-10-10","cited_by_count":110},{"id":"1802.03042","title":"Deep Hedging","created":"2018-02-08","cited_by_count":108},{"id":"1809.09441","title":"Temporal Relational Ranking for Stock Prediction","created":"2018-09-25","cited_by_count":102},{"id":"2009.11698","title":"Principles and Practice of Explainable Machine Learning","created":"2020-09-18","cited_by_count":99},{"id":"1905.04914","title":"Learning to Exploit Long-term Relational Dependencies in Knowledge Graphs","created":"2019-05-13","cited_by_count":83},{"id":"2203.12533","title":"Pathways: Asynchronous Distributed Dataflow for ML","created":"2022-03-23","cited_by_count":82},{"id":"1803.04014","title":"NVIDIA Tensor Core Programmability, Performance & Precision","created":"2018-03-11","cited_by_count":79},{"id":"1910.08892","title":"Bayesian Symbolic Regression","created":"2019-10-20","cited_by_count":78},{"id":"2103.03036","title":"A Survey on Graph Structure Learning: Progress and Opportunities","created":"2021-03-04","cited_by_count":71},{"id":"1906.08495","title":"Probabilistic Logic Neural Networks for Reasoning","created":"2019-06-20","cited_by_count":69},{"id":"1603.01670","title":"Network Morphism","created":"2016-03-05","cited_by_count":65},{"id":"1812.00978","title":"A Survey on Semantic Parsing","created":"2018-12-03","cited_by_count":62},{"id":"1704.02147","title":"Hierarchical Clustering: Objective Functions and Algorithms","created":"2017-04-07","cited_by_count":60},{"id":"1712.02136","title":"Listening to Chaotic Whispers: A Deep Learning Framework for News-oriented Stock Trend Prediction","created":"2017-12-06","cited_by_count":60},{"id":"1704.00764","title":"A Genetic Programming Approach to Designing Convolutional Neural Network Architectures","created":"2017-04-03","cited_by_count":59},{"id":"1506.00379","title":"Modeling Relation Paths for Representation Learning of Knowledge Bases","created":"2015-06-01","cited_by_count":56},{"id":"1711.11231","title":"Knowledge Graph Embedding with Iterative Guidance from Soft Rules","created":"2017-11-30","cited_by_count":51},{"id":"1805.04755","title":"A Simple and Effective Model-Based Variable Importance Measure","created":"2018-05-12","cited_by_count":51},{"id":"2003.01859","title":"Applications of deep learning in stock market prediction: recent progress","created":"2020-02-29","cited_by_count":51},{"id":"2002.03794","title":"The Deep Learning Compiler: A Comprehensive Survey","created":"2020-02-06","cited_by_count":46},{"id":"1712.05191","title":"Relation Extraction : A Survey","created":"2017-12-14","cited_by_count":44},{"id":"1904.12857","title":"AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications","created":"2019-04-29","cited_by_count":40},{"id":"1908.02646","title":"AlphaStock: A Buying-Winners-and-Selling-Losers Investment Strategy using Interpretable Deep Reinforcement Attention Networks","created":"2019-07-24","cited_by_count":40},{"id":"1809.09337","title":"A Survey of Learning Causality with Data: Problems and Methods","created":"2018-09-25","cited_by_count":37},{"id":"1805.02408","title":"Improving Knowledge Graph Embedding Using Simple Constraints","created":"2018-05-07","cited_by_count":36},{"id":"1906.11527","title":"Hyp-RL : Hyperparameter Optimization by Reinforcement Learning","created":"2019-06-27","cited_by_count":36}],"next_cursor":"100"}