{"list":"other","total":58,"rows":[{"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":"1412.6572","title":"Explaining and Harnessing Adversarial Examples","created":"2014-12-20","cited_by_count":7364},{"id":"1502.03167","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","created":"2015-02-11","cited_by_count":7005},{"id":"1706.06083","title":"Towards Deep Learning Models Resistant to Adversarial Attacks","created":"2017-06-19","cited_by_count":6415},{"id":"1603.02754","title":"XGBoost: A Scalable Tree Boosting System","created":"2016-03-09","cited_by_count":5166},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"1611.00712","title":"The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables","created":"2016-11-02","cited_by_count":1148},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2004.05439","title":"Meta-Learning in Neural Networks: A Survey","created":"2020-04-11","cited_by_count":950},{"id":"1611.01236","title":"Adversarial Machine Learning at Scale","created":"2016-11-04","cited_by_count":936},{"id":"2106.11959","title":"Revisiting Deep Learning Models for Tabular Data","created":"2021-06-22","cited_by_count":740},{"id":"2001.03994","title":"Fast is better than free: Revisiting adversarial training","created":"2020-01-12","cited_by_count":727},{"id":"2207.01848","title":"TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second","created":"2022-07-05","cited_by_count":674},{"id":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1908.07442","title":"TabNet: Attentive Interpretable Tabular Learning","created":"2019-08-20","cited_by_count":648},{"id":"1904.12843","title":"Adversarial Training for Free!","created":"2019-04-29","cited_by_count":643},{"id":"1707.00600","title":"Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Ugly","created":"2017-07-03","cited_by_count":538},{"id":"2106.03253","title":"Tabular Data: Deep Learning is Not All You Need","created":"2021-06-06","cited_by_count":535},{"id":"2110.01889","title":"Deep Neural Networks and Tabular Data: A Survey","created":"2021-10-05","cited_by_count":491},{"id":"2012.06678","title":"TabTransformer: Tabular Data Modeling Using Contextual Embeddings","created":"2020-12-11","cited_by_count":409},{"id":"2209.15421","title":"TabDDPM: Modelling Tabular Data with Diffusion Models","created":"2022-09-30","cited_by_count":377},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"2105.11447","title":"True Few-Shot Learning with Language Models","created":"2021-05-24","cited_by_count":344},{"id":"2106.01342","title":"SAINT: Improved Neural Networks for Tabular Data via Row Attention and Contrastive Pre-Training","created":"2021-06-02","cited_by_count":319},{"id":"2210.06280","title":"Language Models are Realistic Tabular Data Generators","created":"2022-10-12","cited_by_count":294},{"id":"1810.03548","title":"Meta-Learning: A Survey","created":"2018-10-08","cited_by_count":256},{"id":"1703.04394","title":"Zero-Shot Learning -- The Good, the Bad and the Ugly","created":"2017-03-13","cited_by_count":255},{"id":"2203.08913","title":"Memorizing Transformers","created":"2022-03-16","cited_by_count":226},{"id":"2305.02997","title":"When Do Neural Nets Outperform Boosted Trees on Tabular Data?","created":"2023-05-04","cited_by_count":223},{"id":"2007.02617","title":"Understanding and Improving Fast Adversarial Training","created":"2020-07-06","cited_by_count":214},{"id":"1909.06312","title":"Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data","created":"2019-09-13","cited_by_count":203},{"id":"2203.05556","title":"On Embeddings for Numerical Features in Tabular Deep Learning","created":"2022-03-10","cited_by_count":186},{"id":"1905.00877","title":"You Only Propagate Once: Accelerating Adversarial Training via Maximal Principle","created":"2019-05-02","cited_by_count":183},{"id":"1708.03731","title":"OpenML Benchmarking Suites","created":"2017-08-11","cited_by_count":178},{"id":"2007.04074","title":"Auto-Sklearn 2.0: Hands-free AutoML via Meta-Learning","created":"2020-07-08","cited_by_count":174},{"id":"1808.07233","title":"Neural Architecture Optimization","created":"2018-08-22","cited_by_count":167},{"id":"2106.11189","title":"Well-tuned Simple Nets Excel on Tabular Datasets","created":"2021-06-21","cited_by_count":151},{"id":"2207.04237","title":"Few-shot training LLMs for project-specific code-summarization","created":"2022-07-09","cited_by_count":129},{"id":"2010.03522","title":"A Survey of Deep Meta-Learning","created":"2020-10-07","cited_by_count":100},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98},{"id":"2006.05132","title":"A Survey on Generative Adversarial Networks: Variants, Applications, and Training","created":"2020-06-09","cited_by_count":97},{"id":"2305.06090","title":"XTab: Cross-table Pretraining for Tabular Transformers","created":"2023-05-10","cited_by_count":81},{"id":"2010.01799","title":"Understanding Catastrophic Overfitting in Single-step Adversarial Training","created":"2020-10-05","cited_by_count":76},{"id":"2402.16785","title":"CARTE: Pretraining and Transfer for Tabular Learning","created":"2024-02-26","cited_by_count":76},{"id":"2406.12031","title":"Large Scale Transfer Learning for Tabular Data via Language Modeling","created":"2024-06-17","cited_by_count":76},{"id":"2307.14338","title":"TabR: Tabular Deep Learning Meets Nearest Neighbors in 2023","created":"2023-07-26","cited_by_count":74},{"id":"2403.16512","title":"LLMs Are Few-Shot In-Context Low-Resource Language Learners","created":"2024-03-25","cited_by_count":68},{"id":"2305.11097","title":"Statistical Foundations of Prior-Data Fitted Networks","created":"2023-05-18","cited_by_count":65},{"id":"2403.01841","title":"Making Pre-trained Language Models Great on Tabular Prediction","created":"2024-03-04","cited_by_count":57},{"id":"2206.15306","title":"Transfer Learning with Deep Tabular Models","created":"2022-06-30","cited_by_count":52},{"id":"2303.00918","title":"STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables","created":"2023-03-02","cited_by_count":49},{"id":"2207.03208","title":"Revisiting Pretraining Objectives for Tabular Deep Learning","created":"2022-07-07","cited_by_count":43},{"id":"1411.2168","title":"On the Characterization of Local Nash Equilibria in Continuous Games","created":"2014-11-08","cited_by_count":22},{"id":"2307.04308","title":"Towards Cross-Table Masked Pretraining for Web Data Mining","created":"2023-07-10","cited_by_count":21},{"id":"2410.13516","title":"PORTAL: Scalable Tabular Foundation Models via Content-Specific Tokenization","created":"2024-10-17","cited_by_count":14},{"id":"2103.06435","title":"Population-Based Evolution Optimizes a Meta-Learning Objective","created":"2021-03-11","cited_by_count":3}],"next_cursor":null}