{"list":"other","total":92,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1705.07115","title":"Multi-Task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics","created":"2017-05-19","cited_by_count":1358},{"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":"1705.05363","title":"Curiosity-driven Exploration by Self-supervised Prediction","created":"2017-05-15","cited_by_count":1194},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1711.07280","title":"Vision-and-Language Navigation: Interpreting visually-grounded navigation instructions in real environments","created":"2017-11-20","cited_by_count":1027},{"id":"1802.01561","title":"IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures","created":"2018-02-05","cited_by_count":883},{"id":"1712.05474","title":"AI2-THOR: An Interactive 3D Environment for Visual AI","created":"2017-12-14","cited_by_count":869},{"id":"1707.08114","title":"A Survey on Multi-Task Learning","created":"2017-07-25","cited_by_count":840},{"id":"1711.02257","title":"GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks","created":"2017-11-07","cited_by_count":834},{"id":"1810.04650","title":"Multi-Task Learning as Multi-Objective Optimization","created":"2018-10-10","cited_by_count":821},{"id":"1706.05098","title":"An Overview of Multi-Task Learning in Deep Neural Networks","created":"2017-06-15","cited_by_count":803},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"id":"1808.10654","title":"Gibson Env: Real-World Perception for Embodied Agents","created":"2018-08-31","cited_by_count":481},{"id":"1611.08974","title":"Semantic Scene Completion from a Single Depth Image","created":"2016-11-28","cited_by_count":472},{"id":"1604.03539","title":"Cross-stitch Networks for Multi-task Learning","created":"2016-04-12","cited_by_count":467},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"1511.06295","title":"Policy Distillation","created":"2015-11-19","cited_by_count":440},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2009.09796","title":"Multi-Task Learning with Deep Neural Networks: A Survey","created":"2020-09-10","cited_by_count":375},{"id":"1609.05143","title":"Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning","created":"2016-09-16","cited_by_count":366},{"id":"1806.02724","title":"Speaker-Follower Models for Vision-and-Language Navigation","created":"2018-06-07","cited_by_count":340},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2004.05155","title":"Learning to Explore using Active Neural SLAM","created":"2020-04-10","cited_by_count":316},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"1912.02315","title":"12-in-1: Multi-Task Vision and Language Representation Learning","created":"2019-12-05","cited_by_count":278},{"id":"1907.04957","title":"Vision-and-Dialog Navigation","created":"2019-07-10","cited_by_count":250},{"id":"1904.04195","title":"Learning to Navigate Unseen Environments: Back Translation with Environmental Dropout","created":"2019-04-08","cited_by_count":244},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"1811.12354","title":"Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments","created":"2018-11-29","cited_by_count":239},{"id":"1707.04175","title":"Distral: Robust Multitask Reinforcement Learning","created":"2017-07-13","cited_by_count":233},{"id":"2002.10638","title":"Towards Learning a Generic Agent for Vision-and-Language Navigation via Pre-training","created":"2020-02-25","cited_by_count":231},{"id":"1805.04409","title":"PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing","created":"2018-05-11","cited_by_count":224},{"id":"1702.03920","title":"Cognitive Mapping and Planning for Visual Navigation","created":"2017-02-13","cited_by_count":212},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1611.03673","title":"Learning to Navigate in Complex Environments","created":"2016-11-11","cited_by_count":198},{"id":"2005.12256","title":"Neural Topological SLAM for Visual Navigation","created":"2020-05-25","cited_by_count":195},{"id":"2102.10772","title":"UniT: Multimodal Multitask Learning with a Unified Transformer","created":"2021-02-22","cited_by_count":195},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"1911.07883","title":"Vision-Language Navigation with Self-Supervised Auxiliary Reasoning Tasks","created":"2019-11-18","cited_by_count":179},{"id":"1511.06342","title":"Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning","created":"2015-11-19","cited_by_count":178},{"id":"2004.14973","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","created":"2020-04-30","cited_by_count":177},{"id":"1901.03035","title":"Self-Monitoring Navigation Agent via Auxiliary Progress Estimation","created":"2019-01-10","cited_by_count":176},{"id":"1707.02286","title":"Emergence of Locomotion Behaviours in Rich Environments","created":"2017-07-07","cited_by_count":165},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"1809.04474","title":"Multi-task Deep Reinforcement Learning with PopArt","created":"2018-09-12","cited_by_count":141},{"id":"2108.09105","title":"Airbert: In-domain Pretraining for Vision-and-Language Navigation","created":"2021-08-20","cited_by_count":130},{"id":"1803.09956","title":"Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning","created":"2018-03-27","cited_by_count":128},{"id":"1810.06543","title":"Visual Semantic Navigation using Scene Priors","created":"2018-10-15","cited_by_count":128},{"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":"2012.05292","title":"Topological Planning with Transformers for Vision-and-Language Navigation","created":"2020-12-09","cited_by_count":116},{"id":"1801.02209","title":"Building Generalizable Agents with a Realistic and Rich 3D Environment","created":"2018-01-07","cited_by_count":109},{"id":"1903.03878","title":"Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks","created":"2019-03-09","cited_by_count":107},{"id":"1909.01871","title":"Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning","created":"2019-09-04","cited_by_count":100},{"id":"2103.03454","title":"Structured Scene Memory for Vision-Language Navigation","created":"2021-03-05","cited_by_count":95},{"id":"1702.08360","title":"Neural Map: Structured Memory for Deep Reinforcement Learning","created":"2017-02-27","cited_by_count":90},{"id":"1706.05137","title":"One Model To Learn Them All","created":"2017-06-16","cited_by_count":87},{"id":"1904.11740","title":"Representation Similarity Analysis for Efficient Task taxonomy & Transfer Learning","created":"2019-04-26","cited_by_count":86},{"id":"2012.11583","title":"Semantic Audio-Visual Navigation","created":"2020-12-21","cited_by_count":82},{"id":"1812.04155","title":"Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention","created":"2018-12-10","cited_by_count":77},{"id":"2007.14626","title":"Object-and-Action Aware Model for Visual Language Navigation","created":"2020-07-29","cited_by_count":77},{"id":"2007.05655","title":"Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation","created":"2020-07-11","cited_by_count":71},{"id":"1906.09237","title":"Shaping Belief States with Generative Environment Models for RL","created":"2019-06-21","cited_by_count":66},{"id":"1610.05182","title":"Learning and Transfer of Modulated Locomotor Controllers","created":"2016-10-17","cited_by_count":59},{"id":"1702.08303","title":"Identifying beneficial task relations for multi-task learning in deep neural networks","created":"2017-02-27","cited_by_count":59},{"id":"2207.11201","title":"Target-Driven Structured Transformer Planner for Vision-Language Navigation","created":"2022-07-19","cited_by_count":58},{"id":"1906.00347","title":"Are You Looking? Grounding to Multiple Modalities in Vision-and-Language Navigation","created":"2019-06-02","cited_by_count":55},{"id":"2007.08037","title":"Active Visual Information Gathering for Vision-Language Navigation","created":"2020-07-15","cited_by_count":55},{"id":"1811.06031","title":"A Hierarchical Multi-task Approach for Learning Embeddings from Semantic Tasks","created":"2018-11-14","cited_by_count":54},{"id":"2007.04561","title":"Auxiliary Tasks Speed Up Learning PointGoal Navigation","created":"2020-07-09","cited_by_count":54},{"id":"2105.09447","title":"VTNet: Visual Transformer Network for Object Goal Navigation","created":"2021-05-20","cited_by_count":51},{"id":"2203.16586","title":"Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation","created":"2022-03-30","cited_by_count":51},{"id":"1903.12117","title":"Many Task Learning with Task Routing","created":"2019-03-28","cited_by_count":50},{"id":"1909.04306","title":"Bayesian Relational Memory for Semantic Visual Navigation","created":"2019-09-10","cited_by_count":48},{"id":"2003.00443","title":"Environment-agnostic Multitask Learning for Natural Language Grounded Navigation","created":"2020-03-01","cited_by_count":43},{"id":"1911.07450","title":"Unsupervised Reinforcement Learning of Transferable Meta-Skills for Embodied Navigation","created":"2019-11-18","cited_by_count":40},{"id":"1609.09025","title":"Learning to Push by Grasping: Using multiple tasks for effective learning","created":"2016-09-28","cited_by_count":37},{"id":"1806.06408","title":"Gated Path Planning Networks","created":"2018-06-17","cited_by_count":31},{"id":"1905.07512","title":"SplitNet: Sim2Sim and Task2Task Transfer for Embodied Visual Navigation","created":"2019-05-18","cited_by_count":29},{"id":"2010.07494","title":"Knowledge Transfer in Multi-Task Deep Reinforcement Learning for Continuous Control","created":"2020-10-15","cited_by_count":28},{"id":"1907.07804","title":"OmniNet: A unified architecture for multi-modal multi-task learning","created":"2019-07-17","cited_by_count":25},{"id":"1911.07308","title":"Counterfactual Vision-and-Language Navigation via Adversarial Path Sampling","created":"2019-11-17","cited_by_count":22},{"id":"1801.08214","title":"Active Neural Localization","created":"2018-01-24","cited_by_count":18},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18},{"id":"1902.01385","title":"Embodied Multimodal Multitask Learning","created":"2019-02-04","cited_by_count":13}],"next_cursor":null}