{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1409.0473","title":"Neural Machine Translation by Jointly Learning to Align and Translate","created":"2014-09-01","cited_by_count":4548},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1701.06538","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","created":"2017-01-23","cited_by_count":3509},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"1311.2901","title":"Visualizing and Understanding Convolutional Networks","created":"2013-11-12","cited_by_count":2290},{"id":"1907.02893","title":"Invariant Risk Minimization","created":"2019-07-05","cited_by_count":1854},{"id":"2006.16241","title":"The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalization","created":"2020-06-29","cited_by_count":1850},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1502.03044","title":"Show, Attend and Tell: Neural Image Caption Generation with Visual Attention","created":"2015-02-10","cited_by_count":1423},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"2009.09761","title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis","created":"2020-09-21","cited_by_count":1354},{"id":"1911.08265","title":"Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model","created":"2019-11-19","cited_by_count":1353},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"1912.06680","title":"Dota 2 with Large Scale Deep Reinforcement Learning","created":"2019-12-13","cited_by_count":1103},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"1611.08097","title":"Geometric deep learning: going beyond Euclidean data","created":"2016-11-24","cited_by_count":1048},{"id":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1404.7828","title":"Deep Learning in Neural Networks: An Overview","created":"2014-04-30","cited_by_count":770},{"id":"1912.02292","title":"Deep Double Descent: Where Bigger Models and More Data Hurt","created":"2019-12-04","cited_by_count":672},{"id":"1410.5401","title":"Neural Turing Machines","created":"2014-10-20","cited_by_count":644},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2106.04803","title":"CoAtNet: Marrying Convolution and Attention for All Data Sizes","created":"2021-06-09","cited_by_count":569},{"id":"1603.08983","title":"Adaptive Computation Time for Recurrent Neural Networks","created":"2016-03-29","cited_by_count":506},{"id":"1611.02779","title":"RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning","created":"2016-11-09","cited_by_count":503},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502},{"id":"1611.05763","title":"Learning to reinforcement learn","created":"2016-11-17","cited_by_count":377},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2003.13350","title":"Agent57: Outperforming the Atari Human Benchmark","created":"2020-03-30","cited_by_count":303},{"id":"2011.15091","title":"Inductive Biases for Deep Learning of Higher-Level Cognition","created":"2020-11-30","cited_by_count":275},{"id":"2012.05876","title":"Neurosymbolic AI: The 3rd Wave","created":"2020-12-10","cited_by_count":255},{"id":"1402.0590","title":"A Survey of Multi-Objective Sequential Decision-Making","created":"2014-02-04","cited_by_count":242},{"id":"2004.10151","title":"Experience Grounds Language","created":"2020-04-21","cited_by_count":242},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1701.01724","title":"DeepStack: Expert-Level Artificial Intelligence in No-Limit Poker","created":"2017-01-06","cited_by_count":233},{"id":"1802.07740","title":"Machine Theory of Mind","created":"2018-02-21","cited_by_count":226},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1801.00631","title":"Deep Learning: A Critical Appraisal","created":"2018-01-02","cited_by_count":217},{"id":"1312.5663","title":"k-Sparse Autoencoders","created":"2013-12-19","cited_by_count":215},{"id":"1902.03545","title":"Task2Vec: Task Embedding for Meta-Learning","created":"2019-02-10","cited_by_count":205},{"id":"2002.06177","title":"The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence","created":"2020-02-14","cited_by_count":195},{"id":"2107.12808","title":"Open-Ended Learning Leads to Generally Capable Agents","created":"2021-07-27","cited_by_count":182},{"id":"2202.09729","title":"It's Raw! Audio Generation with State-Space Models","created":"2022-02-20","cited_by_count":171},{"id":"1901.10912","title":"A Meta-Transfer Objective for Learning to Disentangle Causal Mechanisms","created":"2019-01-30","cited_by_count":158},{"id":"2201.08299","title":"Goal-Conditioned Reinforcement Learning: Problems and Solutions","created":"2022-01-20","cited_by_count":158},{"id":"2110.14051","title":"A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challenges","created":"2021-10-26","cited_by_count":154},{"id":"1703.01988","title":"Neural Episodic Control","created":"2017-03-06","cited_by_count":151},{"id":"1709.08071","title":"Autonomous Agents Modelling Other Agents: A Comprehensive Survey and Open Problems","created":"2017-09-23","cited_by_count":131},{"id":"1711.01239","title":"Routing Networks: Adaptive Selection of Non-linear Functions for Multi-Task Learning","created":"2017-11-03","cited_by_count":126},{"id":"2109.05070","title":"Instance-Conditioned GAN","created":"2021-09-10","cited_by_count":121},{"id":"1910.01075","title":"Learning Neural Causal Models from Unknown Interventions","created":"2019-10-02","cited_by_count":113},{"id":"2101.06046","title":"Counterfactual Generative Networks","created":"2021-01-15","cited_by_count":111},{"id":"1709.08568","title":"The Consciousness Prior","created":"2017-09-25","cited_by_count":107},{"id":"1606.04460","title":"Model-Free Episodic Control","created":"2016-06-14","cited_by_count":102},{"id":"2005.12126","title":"Learning to Simulate Dynamic Environments with GameGAN","created":"2020-05-25","cited_by_count":86},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85},{"id":"1811.06272","title":"Woulda, Coulda, Shoulda: Counterfactually-Guided Policy Search","created":"2018-11-15","cited_by_count":82},{"id":"1812.07671","title":"Deep Online Learning via Meta-Learning: Continual Adaptation for Model-Based RL","created":"2018-12-18","cited_by_count":81},{"id":"1905.03030","title":"Meta-learning of Sequential Strategies","created":"2019-05-08","cited_by_count":70},{"id":"1811.01458","title":"Bayesian Action Decoder for Deep Multi-Agent Reinforcement Learning","created":"2018-11-04","cited_by_count":68},{"id":"2011.09464","title":"Counterfactual Credit Assignment in Model-Free Reinforcement Learning","created":"2020-11-18","cited_by_count":64},{"id":"1706.04317","title":"Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics","created":"2017-06-14","cited_by_count":58},{"id":"2002.04806","title":"The Unreasonable Effectiveness of Deep Learning in Artificial Intelligence","created":"2020-02-12","cited_by_count":57},{"id":"2112.15422","title":"Scalar reward is not enough: A response to Silver, Singh, Precup and Sutton (2021)","created":"2021-11-25","cited_by_count":55},{"id":"1806.10166","title":"Modular meta-learning","created":"2018-06-26","cited_by_count":51},{"id":"1903.11257","title":"How Can We Be So Dense? The Benefits of Using Highly Sparse Representations","created":"2019-03-27","cited_by_count":45},{"id":"2105.14039","title":"Towards mental time travel: a hierarchical memory for reinforcement learning agents","created":"2021-05-28","cited_by_count":40},{"id":"2106.14421","title":"Causal Reinforcement Learning using Observational and Interventional Data","created":"2021-06-28","cited_by_count":39},{"id":"1808.07784","title":"Time-Agnostic Prediction: Predicting Predictable Video Frames","created":"2018-08-23","cited_by_count":37},{"id":"2012.10390","title":"Deep Learning and the Global Workspace Theory","created":"2020-12-04","cited_by_count":36},{"id":"2111.01587","title":"Procedural Generalization by Planning with Self-Supervised World Models","created":"2021-11-02","cited_by_count":31},{"id":"2010.13382","title":"FastFormers: Highly Efficient Transformer Models for Natural Language Understanding","created":"2020-10-26","cited_by_count":28},{"id":"2106.02097","title":"A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning","created":"2021-06-03","cited_by_count":27},{"id":"2107.13704","title":"A Theory of Consciousness from a Theoretical Computer Science Perspective: Insights from the Conscious Turing Machine","created":"2021-07-29","cited_by_count":22},{"id":"1802.08864","title":"One Big Net For Everything","created":"2018-02-24","cited_by_count":16},{"id":"1808.04768","title":"Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models","created":"2018-08-14","cited_by_count":12},{"id":"1907.04964","title":"A Model-based Approach for Sample-efficient Multi-task Reinforcement Learning","created":"2019-07-11","cited_by_count":12},{"id":"1804.09401","title":"Generative Temporal Models with Spatial Memory for Partially Observed Environments","created":"2018-04-25","cited_by_count":10},{"id":"1705.02670","title":"Metacontrol for Adaptive Imagination-Based Optimization","created":"2017-05-07","cited_by_count":8},{"id":"1807.03149","title":"Learning models for visual 3D localization with implicit mapping","created":"2018-07-04","cited_by_count":7},{"id":"2202.01682","title":"How to build a cognitive map: insights from models of the hippocampal formation","created":"2022-02-03","cited_by_count":5},{"id":"1911.09560","title":"Memory-Efficient Episodic Control Reinforcement Learning with Dynamic Online k-means","created":"2019-11-21","cited_by_count":3}],"next_cursor":null}