{"list":"other","total":51,"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":"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":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"1703.03400","title":"Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks","created":"2017-03-09","cited_by_count":4897},{"id":"1901.02860","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","created":"2019-01-09","cited_by_count":1850},{"id":"2111.02080","title":"An Explanation of In-context Learning as Implicit Bayesian Inference","created":"2021-11-03","cited_by_count":938},{"id":"1908.03265","title":"On the Variance of the Adaptive Learning Rate and Beyond","created":"2019-08-08","cited_by_count":772},{"id":"2208.01066","title":"What Can Transformers Learn In-Context? A Case Study of Simple Function Classes","created":"2022-08-01","cited_by_count":715},{"id":"1807.03819","title":"Universal Transformers","created":"2018-07-10","cited_by_count":647},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2110.15943","title":"MetaICL: Learning to Learn In Context","created":"2021-10-29","cited_by_count":454},{"id":"2210.00720","title":"Complexity-Based Prompting for Multi-Step Reasoning","created":"2022-10-03","cited_by_count":388},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1908.08351","title":"Compositionality decomposed: how do neural networks generalise?","created":"2019-08-22","cited_by_count":265},{"id":"2010.05465","title":"COGS: A Compositional Generalization Challenge Based on Semantic Interpretation","created":"2020-10-12","cited_by_count":263},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"1601.01280","title":"Language to Logical Form with Neural Attention","created":"2016-01-06","cited_by_count":158},{"id":"1904.09545","title":"Good-Enough Compositional Data Augmentation","created":"2019-04-21","cited_by_count":158},{"id":"2010.12725","title":"Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?","created":"2020-10-24","cited_by_count":147},{"id":"2108.12284","title":"The Devil is in the Detail: Simple Tricks Improve Systematic Generalization of Transformers","created":"2021-08-26","cited_by_count":117},{"id":"1808.08437","title":"Meta-Learning for Low-Resource Neural Machine Translation","created":"2018-08-25","cited_by_count":105},{"id":"2212.04458","title":"General-Purpose In-Context Learning by Meta-Learning Transformers","created":"2022-12-08","cited_by_count":105},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2007.08970","title":"Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures","created":"2020-07-17","cited_by_count":95},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2108.04378","title":"Making Transformers Solve Compositional Tasks","created":"2021-08-09","cited_by_count":72},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"2003.02739","title":"Zero-Shot Cross-Lingual Transfer with Meta Learning","created":"2020-03-05","cited_by_count":66},{"id":"2010.03706","title":"Learning to Recombine and Resample Data for Compositional Generalization","created":"2020-10-08","cited_by_count":65},{"id":"2106.04252","title":"Meta-Learning to Compositionally Generalize","created":"2021-06-08","cited_by_count":62},{"id":"1904.00157","title":"Linguistic generalization and compositionality in modern artificial neural networks","created":"2019-03-30","cited_by_count":58},{"id":"1904.09708","title":"Compositional generalization in a deep seq2seq model by separating syntax and semantics","created":"2019-04-22","cited_by_count":56},{"id":"2104.07478","title":"Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representations","created":"2021-04-15","cited_by_count":55},{"id":"2006.10627","title":"Compositional Generalization by Learning Analytical Expressions","created":"2020-06-18","cited_by_count":53},{"id":"2305.04835","title":"How Do In-Context Examples Affect Compositional Generalization?","created":"2023-05-08","cited_by_count":51},{"id":"2205.12253","title":"Evaluating the Impact of Model Scale for Compositional Generalization in Semantic Parsing","created":"2022-05-24","cited_by_count":50},{"id":"1910.02612","title":"Compositional Generalization for Primitive Substitutions","created":"2019-10-07","cited_by_count":48},{"id":"2010.07174","title":"The EOS Decision and Length Extrapolation","created":"2020-10-14","cited_by_count":46},{"id":"1906.03520","title":"Domain Adaptive Dialog Generation via Meta Learning","created":"2019-06-08","cited_by_count":41},{"id":"2112.00578","title":"Systematic Generalization with Edge Transformers","created":"2021-12-01","cited_by_count":38},{"id":"2010.07792","title":"Hierarchical Poset Decoding for Compositional Generalization in Language","created":"2020-10-15","cited_by_count":26},{"id":"2211.08473","title":"On the Compositional Generalization Gap of In-Context Learning","created":"2022-11-15","cited_by_count":24},{"id":"2203.07402","title":"Revisiting the Compositional Generalization Abilities of Neural Sequence Models","created":"2022-03-14","cited_by_count":20},{"id":"2012.04276","title":"Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization","created":"2020-12-08","cited_by_count":19},{"id":"2109.15256","title":"Inducing Transformer's Compositional Generalization Ability via Auxiliary Sequence Prediction Tasks","created":"2021-09-30","cited_by_count":19},{"id":"2306.02840","title":"Learning to Substitute Spans towards Improving Compositional Generalization","created":"2023-06-05","cited_by_count":8}],"next_cursor":null}