{"list":"other","total":179,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1612.00796","title":"Overcoming catastrophic forgetting in neural networks","created":"2016-12-02","cited_by_count":4787},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"1606.09282","title":"Learning without Forgetting","created":"2016-06-29","cited_by_count":2496},{"id":"1803.03635","title":"The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks","created":"2018-03-09","cited_by_count":2262},{"id":"2005.01643","title":"Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problems","created":"2020-05-04","cited_by_count":1920},{"id":"1706.08840","title":"Gradient Episodic Memory for Continual Learning","created":"2017-06-26","cited_by_count":1898},{"id":"1606.01540","title":"OpenAI Gym","created":"2016-06-05","cited_by_count":1736},{"id":"1606.04671","title":"Progressive Neural Networks","created":"2016-06-15","cited_by_count":1361},{"id":"1802.07569","title":"Continual Lifelong Learning with Neural Networks: A Review","created":"2018-02-21","cited_by_count":1330},{"id":"1910.10897","title":"Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning","created":"2019-10-24","cited_by_count":1204},{"id":"1705.08690","title":"Continual Learning with Deep Generative Replay","created":"2017-05-24","cited_by_count":1158},{"id":"1811.11682","title":"Experience Replay for Continual Learning","created":"2018-11-28","cited_by_count":1095},{"id":"1812.00420","title":"Efficient Lifelong Learning with A-GEM","created":"2018-12-02","cited_by_count":1058},{"id":"2004.07211","title":"Dark Experience for General Continual Learning: a Strong, Simple Baseline","created":"2020-04-15","cited_by_count":911},{"id":"1801.10112","title":"Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence","created":"2018-01-30","cited_by_count":742},{"id":"1708.01547","title":"Lifelong Learning with Dynamically Expandable Networks","created":"2017-08-04","cited_by_count":694},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"1801.01423","title":"Overcoming catastrophic forgetting with hard attention to the task","created":"2018-01-04","cited_by_count":681},{"id":"1904.07734","title":"Three scenarios for continual learning","created":"2019-04-15","cited_by_count":614},{"id":"1903.08671","title":"Gradient based sample selection for online continual learning","created":"2019-03-20","cited_by_count":571},{"id":"1810.11910","title":"Learning to Learn without Forgetting by Maximizing Transfer and Minimizing Interference","created":"2018-10-29","cited_by_count":521},{"id":"1805.06370","title":"Progress & Compress: A scalable framework for continual learning","created":"2018-05-16","cited_by_count":520},{"id":"1609.05140","title":"The Option-Critic Architecture","created":"2016-09-16","cited_by_count":448},{"id":"1908.04742","title":"Online Continual Learning with Maximally Interfered Retrieval","created":"2019-08-11","cited_by_count":379},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2006.12983","title":"dm_control: Software and Tasks for Continuous Control","created":"2020-06-22","cited_by_count":375},{"id":"1611.06194","title":"Expert Gate: Lifelong Learning with a Network of Experts","created":"2016-11-18","cited_by_count":372},{"id":"1701.08734","title":"PathNet: Evolution Channels Gradient Descent in Super Neural Networks","created":"2017-01-30","cited_by_count":364},{"id":"2103.09762","title":"Gradient Projection Memory for Continual Learning","created":"2021-03-17","cited_by_count":348},{"id":"1710.10628","title":"Variational Continual Learning","created":"2017-10-29","cited_by_count":339},{"id":"1703.01161","title":"FeUdal Networks for Hierarchical Reinforcement Learning","created":"2017-03-03","cited_by_count":337},{"id":"1904.00310","title":"Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting","created":"2019-03-31","cited_by_count":302},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"1708.04782","title":"StarCraft II: A New Challenge for Reinforcement Learning","created":"2017-08-16","cited_by_count":274},{"id":"2012.13490","title":"Towards Continual Reinforcement Learning: A Review and Perspectives","created":"2020-12-25","cited_by_count":274},{"id":"1906.00695","title":"Continual learning with hypernetworks","created":"2019-06-03","cited_by_count":273},{"id":"1802.10269","title":"Selective Experience Replay for Lifelong Learning","created":"2018-02-28","cited_by_count":241},{"id":"1909.10893","title":"Recurrent Independent Mechanisms","created":"2019-09-24","cited_by_count":219},{"id":"1910.06562","title":"Compacting, Picking and Growing for Unforgetting Continual Learning","created":"2019-10-15","cited_by_count":207},{"id":"1805.07810","title":"Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting","created":"2018-05-20","cited_by_count":201},{"id":"2006.03875","title":"Coresets via Bilevel Optimization for Continual Learning and Streaming","created":"2020-06-06","cited_by_count":192},{"id":"1905.12588","title":"Meta-Learning Representations for Continual Learning","created":"2019-05-29","cited_by_count":189},{"id":"1906.01076","title":"Episodic Memory in Lifelong Language Learning","created":"2019-06-03","cited_by_count":188},{"id":"2006.06958","title":"Understanding the Role of Training Regimes in Continual Learning","created":"2020-06-12","cited_by_count":180},{"id":"2003.03196","title":"Federated Continual Learning with Weighted Inter-client Transfer","created":"2020-03-06","cited_by_count":161},{"id":"2007.07400","title":"Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics","created":"2020-07-14","cited_by_count":161},{"id":"1909.03329","title":"LAMOL: LAnguage MOdeling for Lifelong Language Learning","created":"2019-09-07","cited_by_count":160},{"id":"2012.09823","title":"Continual Lifelong Learning in Natural Language Processing: A Survey","created":"2020-12-17","cited_by_count":152},{"id":"1910.14481","title":"Continual Unsupervised Representation Learning","created":"2019-10-31","cited_by_count":147},{"id":"1905.11614","title":"Uncertainty-based Continual Learning with Adaptive Regularization","created":"2019-05-28","cited_by_count":146},{"id":"2010.04495","title":"Linear Mode Connectivity in Multitask and Continual Learning","created":"2020-10-09","cited_by_count":145},{"id":"2003.13661","title":"Multi-Task Reinforcement Learning with Soft Modularization","created":"2020-03-30","cited_by_count":143},{"id":"2001.00689","title":"A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning","created":"2020-01-03","cited_by_count":134},{"id":"1705.03633","title":"Inferring and Executing Programs for Visual Reasoning","created":"2017-05-10","cited_by_count":130},{"id":"1609.07088","title":"Learning Modular Neural Network Policies for Multi-Task and Multi-Robot Transfer","created":"2016-09-22","cited_by_count":127},{"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":"1704.05526","title":"Learning to Reason: End-to-End Module Networks for Visual Question Answering","created":"2017-04-18","cited_by_count":125},{"id":"1902.09432","title":"Scalable and Order-robust Continual Learning with Additive Parameter Decomposition","created":"2019-02-25","cited_by_count":125},{"id":"1901.11356","title":"Functional Regularisation for Continual Learning with Gaussian Processes","created":"2019-01-31","cited_by_count":123},{"id":"2007.04976","title":"One Policy to Control Them All: Shared Modular Policies for Agent-Agnostic Control","created":"2020-07-09","cited_by_count":121},{"id":"2105.10919","title":"Continual World: A Robotic Benchmark For Continual Reinforcement Learning","created":"2021-05-23","cited_by_count":116},{"id":"2010.04296","title":"CausalWorld: A Robotic Manipulation Benchmark for Causal Structure and Transfer Learning","created":"2020-10-08","cited_by_count":109},{"id":"1905.09808","title":"MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies","created":"2019-05-23","cited_by_count":108},{"id":"2003.13726","title":"Continual Learning with Node-Importance based Adaptive Group Sparse Regularization","created":"2020-03-30","cited_by_count":105},{"id":"2004.14070","title":"Continual Deep Learning by Functional Regularisation of Memorable Past","created":"2020-04-29","cited_by_count":105},{"id":"1805.08289","title":"Measuring and regularizing networks in function space","created":"2018-05-21","cited_by_count":99},{"id":"1906.05381","title":"Compositional generalization through meta sequence-to-sequence learning","created":"2019-06-12","cited_by_count":99},{"id":"2010.11635","title":"Continual Learning in Low-rank Orthogonal Subspaces","created":"2020-10-22","cited_by_count":99},{"id":"2010.02066","title":"Are Neural Nets Modular? Inspecting Functional Modularity Through Differentiable Weight Masks","created":"2020-10-05","cited_by_count":98},{"id":"1907.00182","title":"Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges","created":"2019-06-29","cited_by_count":93},{"id":"2112.02706","title":"Achieving Forgetting Prevention and Knowledge Transfer in Continual Learning","created":"2021-12-05","cited_by_count":91},{"id":"1604.07255","title":"A Deep Hierarchical Approach to Lifelong Learning in Minecraft","created":"2016-04-25","cited_by_count":90},{"id":"1901.10964","title":"Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement","created":"2019-01-30","cited_by_count":88},{"id":"2012.12631","title":"Efficient Continual Learning with Modular Networks and Task-Driven Priors","created":"2020-12-23","cited_by_count":88},{"id":"2107.04384","title":"Continual Learning in the Teacher-Student Setup: Impact of Task Similarity","created":"2021-07-09","cited_by_count":88},{"id":"2006.05188","title":"Optimal Continual Learning has Perfect Memory and is NP-hard","created":"2020-06-09","cited_by_count":87},{"id":"2103.01197","title":"Coordination Among Neural Modules Through a Shared Global Workspace","created":"2021-03-01","cited_by_count":85},{"id":"1805.04276","title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","created":"2018-05-11","cited_by_count":84},{"id":"1902.07181","title":"Measuring Compositionality in Representation Learning","created":"2019-02-19","cited_by_count":84},{"id":"2002.09571","title":"Learning to Continually Learn","created":"2020-02-21","cited_by_count":84},{"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":"2112.10017","title":"Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks","created":"2021-12-18","cited_by_count":81},{"id":"2008.06662","title":"Compositional Generalization via Neural-Symbolic Stack Machines","created":"2020-08-15","cited_by_count":80},{"id":"1810.06284","title":"CURIOUS: Intrinsically Motivated Modular Multi-Goal Reinforcement Learning","created":"2018-10-15","cited_by_count":79},{"id":"2006.14610","title":"A causal view of compositional zero-shot recognition","created":"2020-06-25","cited_by_count":78},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"2002.01365","title":"Compositional Languages Emerge in a Neural Iterated Learning Model","created":"2020-02-04","cited_by_count":75},{"id":"2003.05562","title":"Learning Compositional Rules via Neural Program Synthesis","created":"2020-03-12","cited_by_count":74},{"id":"2110.12187","title":"AFEC: Active Forgetting of Negative Transfer in Continual Learning","created":"2021-10-23","cited_by_count":73},{"id":"1803.06773","title":"Composable Deep Reinforcement Learning for Robotic Manipulation","created":"2018-03-19","cited_by_count":72},{"id":"2110.04593","title":"Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learning","created":"2021-10-09","cited_by_count":72},{"id":"1902.05546","title":"Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity","created":"2019-02-14","cited_by_count":70},{"id":"2008.09293","title":"A Composable Specification Language for Reinforcement Learning Tasks","created":"2020-08-21","cited_by_count":69},{"id":"1910.08264","title":"Learning Compositional Koopman Operators for Model-Based Control","created":"2019-10-18","cited_by_count":67},{"id":"2106.13906","title":"Compositional Reinforcement Learning from Logical Specifications","created":"2021-06-25","cited_by_count":67},{"id":"1912.04971","title":"Neural Module Networks for Reasoning over Text","created":"2019-12-10","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":"2111.07736","title":"Continual Learning via Local Module Composition","created":"2021-11-15","cited_by_count":63}],"next_cursor":"100"}