{"list":"other","total":60,"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":"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2111.00396","title":"Efficiently Modeling Long Sequences with Structured State Spaces","created":"2021-10-31","cited_by_count":2465},{"id":"2012.07805","title":"Extracting Training Data from Large Language Models","created":"2020-12-14","cited_by_count":2189},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2001.04451","title":"Reformer: The Efficient Transformer","created":"2020-01-13","cited_by_count":1668},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"1506.06724","title":"Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books","created":"2015-06-22","cited_by_count":1043},{"id":"2112.04359","title":"Ethical and social risks of harm from Language Models","created":"2021-12-08","cited_by_count":966},{"id":"2009.06732","title":"Efficient Transformers: A Survey","created":"2020-09-14","cited_by_count":790},{"id":"2011.04006","title":"Long Range Arena: A Benchmark for Efficient Transformers","created":"2020-11-08","cited_by_count":700},{"id":"1606.04474","title":"Learning to learn by gradient descent by gradient descent","created":"2016-06-14","cited_by_count":620},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"2008.02217","title":"Hopfield Networks is All You Need","created":"2020-07-16","cited_by_count":475},{"id":"2003.05997","title":"Efficient Content-Based Sparse Attention with Routing Transformers","created":"2020-03-12","cited_by_count":471},{"id":"1606.01164","title":"Dense Associative Memory for Pattern Recognition","created":"2016-06-03","cited_by_count":236},{"id":"2004.08249","title":"Understanding the Difficulty of Training Transformers","created":"2020-04-17","cited_by_count":210},{"id":"2103.12828","title":"Learning to Optimize: A Primer and A Benchmark","created":"2021-03-23","cited_by_count":208},{"id":"1606.01885","title":"Learning to Optimize","created":"2016-06-06","cited_by_count":195},{"id":"1812.07252","title":"Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networks","created":"2018-12-18","cited_by_count":174},{"id":"1811.09358","title":"A Sufficient Condition for Convergences of Adam and RMSProp","created":"2018-11-23","cited_by_count":126},{"id":"2008.06996","title":"Large Associative Memory Problem in Neurobiology and Machine Learning","created":"2020-08-16","cited_by_count":112},{"id":"1703.04813","title":"Learned Optimizers that Scale and Generalize","created":"2017-03-14","cited_by_count":110},{"id":"1804.09849","title":"The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation","created":"2018-04-26","cited_by_count":102},{"id":"1810.10180","title":"Understanding and correcting pathologies in the training of learned optimizers","created":"2018-10-24","cited_by_count":97},{"id":"2205.13320","title":"Towards Learning Universal Hyperparameter Optimizers with Transformers","created":"2022-05-26","cited_by_count":81},{"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":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57},{"id":"2107.03974","title":"Offline Meta-Reinforcement Learning with Online Self-Supervision","created":"2021-07-08","cited_by_count":53},{"id":"2112.13835","title":"Unbiased Gradient Estimation in Unrolled Computation Graphs with Persistent Evolution Strategies","created":"2021-12-27","cited_by_count":52},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"2106.12566","title":"Stable, Fast and Accurate: Kernelized Attention with Relative Positional Encoding","created":"2021-06-23","cited_by_count":51},{"id":"1703.03633","title":"Learning Gradient Descent: Better Generalization and Longer Horizons","created":"2017-03-10","cited_by_count":50},{"id":"2106.02695","title":"Meta-Learning with Fewer Tasks through Task Interpolation","created":"2021-06-04","cited_by_count":45},{"id":"1909.05830","title":"Differentially Private Meta-Learning","created":"2019-09-12","cited_by_count":41},{"id":"2107.07999","title":"From block-Toeplitz matrices to differential equations on graphs: towards a general theory for scalable masked Transformers","created":"2021-07-16","cited_by_count":38},{"id":"2102.03832","title":"Generalization of Model-Agnostic Meta-Learning Algorithms: Recurring and Unseen Tasks","created":"2021-02-07","cited_by_count":36},{"id":"2010.09089","title":"Training Stronger Baselines for Learning to Optimize","created":"2020-10-18","cited_by_count":31},{"id":"2209.10780","title":"Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigation","created":"2022-09-22","cited_by_count":29},{"id":"1911.03787","title":"Learning to Optimize in Swarms","created":"2019-11-09","cited_by_count":23},{"id":"2010.13957","title":"MELD: Meta-Reinforcement Learning from Images via Latent State Models","created":"2020-10-26","cited_by_count":22},{"id":"2205.15317","title":"Chefs' Random Tables: Non-Trigonometric Random Features","created":"2022-05-30","cited_by_count":21},{"id":"2012.11346","title":"Sub-Linear Memory: How to Make Performers SLiM","created":"2020-12-21","cited_by_count":18},{"id":"2110.08323","title":"On Learning the Transformer Kernel","created":"2021-10-15","cited_by_count":15},{"id":"2112.04467","title":"CoMPS: Continual Meta Policy Search","created":"2021-12-08","cited_by_count":15},{"id":"2212.01055","title":"Transformer-Based Learned Optimization","created":"2022-12-02","cited_by_count":13},{"id":"2006.01952","title":"Learning Active Task-Oriented Exploration Policies for Bridging the Sim-to-Real Gap","created":"2020-06-02","cited_by_count":11},{"id":"1906.03367","title":"Using learned optimizers to make models robust to input noise","created":"2019-06-08","cited_by_count":10},{"id":"1611.03824","title":"Learning to Learn without Gradient Descent by Gradient Descent","created":"2016-11-11","cited_by_count":9},{"id":"2210.04485","title":"A Memory Transformer Network for Incremental Learning","created":"2022-10-10","cited_by_count":9},{"id":"1902.04811","title":"On Nonconvex Optimization for Machine Learning: Gradients, Stochasticity, and Saddle Points","created":"2019-02-13","cited_by_count":8},{"id":"2109.07081","title":"Optimizing Trajectories with Closed-Loop Dynamic SQP","created":"2021-09-15","cited_by_count":5}],"next_cursor":null}