{"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":"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"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":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"1609.09106","title":"HyperNetworks","created":"2016-09-27","cited_by_count":1027},{"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":"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":"2201.02177","title":"Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets","created":"2022-01-06","cited_by_count":629},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"1807.01613","title":"Conditional Neural Processes","created":"2018-07-04","cited_by_count":426},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"2112.10510","title":"Transformers Can Do Bayesian Inference","created":"2021-12-20","cited_by_count":360},{"id":"1909.09157","title":"Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAML","created":"2019-09-19","cited_by_count":359},{"id":"2205.05055","title":"Data Distributional Properties Drive Emergent In-Context Learning in Transformers","created":"2022-04-22","cited_by_count":309},{"id":"2207.02098","title":"Neural Networks and the Chomsky Hierarchy","created":"2022-07-05","cited_by_count":217},{"id":"2207.04901","title":"Exploring Length Generalization in Large Language Models","created":"2022-07-11","cited_by_count":206},{"id":"2203.01302","title":"Evolving Curricula with Regret-Based Environment Design","created":"2022-03-02","cited_by_count":173},{"id":"1805.09801","title":"Meta-Gradient Reinforcement Learning","created":"2018-05-24","cited_by_count":159},{"id":"2003.03384","title":"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch","created":"2020-03-06","cited_by_count":143},{"id":"2207.04179","title":"Transformer Neural Processes: Uncertainty-Aware Meta Learning Via Sequence Modeling","created":"2022-07-09","cited_by_count":127},{"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":"1912.07768","title":"Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data","created":"2019-12-17","cited_by_count":104},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"2106.06295","title":"Going Beyond Linear Transformers with Recurrent Fast Weight Programmers","created":"2021-06-11","cited_by_count":89},{"id":"1802.04821","title":"Evolved Policy Gradients","created":"2018-02-13","cited_by_count":88},{"id":"1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","created":"2019-05-27","cited_by_count":86},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"id":"2007.08794","title":"Discovering Reinforcement Learning Algorithms","created":"2020-07-17","cited_by_count":77},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"1910.04098","title":"Improving Generalization in Meta Reinforcement Learning using Learned Objectives","created":"2019-10-09","cited_by_count":68},{"id":"1906.05374","title":"Meta-Learning via Learned Loss","created":"2019-06-12","cited_by_count":60},{"id":"2009.11243","title":"Tasks, stability, architecture, and compute: Training more effective learned optimizers, and using them to train themselves","created":"2020-09-23","cited_by_count":58},{"id":"2201.04182","title":"HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning","created":"2022-01-11","cited_by_count":55},{"id":"2109.02869","title":"The Sensory Neuron as a Transformer: Permutation-Invariant Neural Networks for Reinforcement Learning","created":"2021-09-07","cited_by_count":50},{"id":"2012.14905","title":"Meta Learning Backpropagation And Improving It","created":"2020-12-29","cited_by_count":49},{"id":"2101.03958","title":"Evolving Reinforcement Learning Algorithms","created":"2021-01-08","cited_by_count":49},{"id":"2211.11260","title":"Discovering Evolution Strategies via Meta-Black-Box Optimization","created":"2022-11-21","cited_by_count":44},{"id":"2010.11223","title":"Meta-trained agents implement Bayes-optimal agents","created":"2020-10-21","cited_by_count":38},{"id":"2002.11887","title":"Using a thousand optimization tasks to learn hyperparameter search strategies","created":"2020-02-27","cited_by_count":29},{"id":"1611.09913","title":"Capacity and Trainability in Recurrent Neural Networks","created":"2016-11-29","cited_by_count":28},{"id":"2109.10781","title":"Introducing Symmetries to Black Box Meta Reinforcement Learning","created":"2021-09-22","cited_by_count":25},{"id":"2008.07545","title":"Whitening and second order optimization both make information in the dataset unusable during training, and can reduce or prevent generalization","created":"2020-08-17","cited_by_count":15},{"id":"2104.07959","title":"Evolving and Merging Hebbian Learning Rules: Increasing Generalization by Decreasing the Number of Rules","created":"2021-04-16","cited_by_count":12},{"id":"2104.04657","title":"Meta-Learning Bidirectional Update Rules","created":"2021-04-10","cited_by_count":10},{"id":"2205.07868","title":"Minimal Neural Network Models for Permutation Invariant Agents","created":"2022-05-12","cited_by_count":4}],"next_cursor":null}