{"list":"other","total":53,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"id":"1802.05365","title":"Deep contextualized word representations","created":"2018-02-15","cited_by_count":2290},{"id":"1902.01007","title":"Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference","created":"2019-02-04","cited_by_count":876},{"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":"1912.00582","title":"BLiMP: The Benchmark of Linguistic Minimal Pairs for English","created":"2019-12-02","cited_by_count":564},{"id":"2002.08791","title":"Bayesian Deep Learning and a Probabilistic Perspective of Generalization","created":"2020-02-20","cited_by_count":480},{"id":"1310.1531","title":"DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition","created":"2013-10-06","cited_by_count":424},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1611.01368","title":"Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies","created":"2016-11-04","cited_by_count":354},{"id":"1810.09502","title":"How to train your MAML","created":"2018-10-22","cited_by_count":309},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308},{"id":"1608.05859","title":"Using the Output Embedding to Improve Language Models","created":"2016-08-20","cited_by_count":272},{"id":"1808.09031","title":"Targeted Syntactic Evaluation of Language Models","created":"2018-08-27","cited_by_count":242},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"1803.11138","title":"Colorless green recurrent networks dream hierarchically","created":"2018-03-29","cited_by_count":213},{"id":"1806.03836","title":"Bayesian Model-Agnostic Meta-Learning","created":"2018-06-11","cited_by_count":194},{"id":"1801.08930","title":"Recasting Gradient-Based Meta-Learning as Hierarchical Bayes","created":"2018-01-26","cited_by_count":180},{"id":"2005.03692","title":"A Systematic Assessment of Syntactic Generalization in Neural Language Models","created":"2020-05-07","cited_by_count":165},{"id":"2009.06489","title":"The Hardware Lottery","created":"2020-09-14","cited_by_count":160},{"id":"2005.00955","title":"How Can We Accelerate Progress Towards Human-like Linguistic Generalization?","created":"2020-05-03","cited_by_count":114},{"id":"2105.11115","title":"Self-Attention Networks Can Process Bounded Hierarchical Languages","created":"2021-05-24","cited_by_count":105},{"id":"1708.00107","title":"Learned in Translation: Contextualized Word Vectors","created":"2017-08-01","cited_by_count":104},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2111.06077","title":"A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part I: Models and Data Transformations","created":"2021-11-11","cited_by_count":99},{"id":"2208.07998","title":"What Artificial Neural Networks Can Tell Us About Human Language Acquisition","created":"2022-08-17","cited_by_count":99},{"id":"1910.01727","title":"Generalized Inner Loop Meta-Learning","created":"2019-10-03","cited_by_count":93},{"id":"1911.02969","title":"BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance","created":"2019-11-07","cited_by_count":89},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2001.03632","title":"Does syntax need to grow on trees? Sources of hierarchical inductive bias in sequence-to-sequence networks","created":"2020-01-10","cited_by_count":72},{"id":"2305.11097","title":"Statistical Foundations of Prior-Data Fitted Networks","created":"2023-05-18","cited_by_count":65},{"id":"2004.08500","title":"A Formal Hierarchy of RNN Architectures","created":"2020-04-18","cited_by_count":62},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"1603.04351","title":"Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations","created":"2016-03-14","cited_by_count":55},{"id":"2109.14989","title":"Structural Persistence in Language Models: Priming as a Window into Abstract Language Representations","created":"2021-09-30","cited_by_count":44},{"id":"2205.01128","title":"Neurocompositional computing: From the Central Paradox of Cognition to a new generation of AI systems","created":"2022-05-02","cited_by_count":44},{"id":"2006.00555","title":"Transferring Inductive Biases through Knowledge Distillation","created":"2020-05-31","cited_by_count":41},{"id":"2011.13464","title":"Meta-learning in natural and artificial intelligence","created":"2020-11-26","cited_by_count":39},{"id":"2304.13060","title":"Injecting structural hints: Using language models to study inductive biases in language learning","created":"2023-04-25","cited_by_count":35},{"id":"1909.10579","title":"Using Priming to Uncover the Organization of Syntactic Representations in Neural Language Models","created":"2019-09-23","cited_by_count":29},{"id":"2006.16324","title":"Universal linguistic inductive biases via meta-learning","created":"2020-06-29","cited_by_count":29},{"id":"1711.06301","title":"One Model for the Learning of Language","created":"2017-11-16","cited_by_count":22},{"id":"2301.11462","title":"How poor is the stimulus? Evaluating hierarchical generalization in neural networks trained on child-directed speech","created":"2023-01-26","cited_by_count":22},{"id":"1710.03838","title":"The Galactic Dependencies Treebanks: Getting More Data by Synthesizing New Languages","created":"2017-10-10","cited_by_count":19},{"id":"1808.09930","title":"A Neural Model of Adaptation in Reading","created":"2018-08-29","cited_by_count":18},{"id":"1711.06351","title":"Question Asking as Program Generation","created":"2017-11-16","cited_by_count":13}],"next_cursor":null}