{"list":"other","total":63,"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":"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2201.08239","title":"LaMDA: Language Models for Dialog Applications","created":"2022-01-20","cited_by_count":1220},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1511.05952","title":"Prioritized Experience Replay","created":"2015-11-18","cited_by_count":1099},{"id":"2201.07207","title":"Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents","created":"2022-01-18","cited_by_count":1035},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"1912.01734","title":"ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks","created":"2019-12-03","cited_by_count":783},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2203.12601","title":"R3M: A Universal Visual Representation for Robot Manipulation","created":"2022-03-23","cited_by_count":694},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"1803.11175","title":"Universal Sentence Encoder","created":"2018-03-29","cited_by_count":489},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2104.08212","title":"MT-Opt: Continuous Multi-Task Robotic Reinforcement Learning at Scale","created":"2021-04-16","cited_by_count":229},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221},{"id":"1803.00653","title":"Semi-parametric Topological Memory for Navigation","created":"2018-03-01","cited_by_count":209},{"id":"1611.01796","title":"Modular Multitask Reinforcement Learning with Policy Sketches","created":"2016-11-06","cited_by_count":203},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2108.03332","title":"BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environments","created":"2021-08-06","cited_by_count":165},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"1906.03926","title":"A Survey of Reinforcement Learning Informed by Natural Language","created":"2019-06-10","cited_by_count":154},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"id":"2010.12083","title":"Language-Conditioned Imitation Learning for Robot Manipulation Tasks","created":"2020-10-22","cited_by_count":136},{"id":"2104.07749","title":"Actionable Models: Unsupervised Offline Reinforcement Learning of Robotic Skills","created":"2021-04-15","cited_by_count":125},{"id":"2109.01115","title":"Learning Language-Conditioned Robot Behavior from Offline Data and Crowd-Sourced Annotation","created":"2021-09-02","cited_by_count":118},{"id":"1706.06551","title":"Grounded Language Learning in a Simulated 3D World","created":"2017-06-20","cited_by_count":100},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"1706.05064","title":"Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning","created":"2017-06-15","cited_by_count":98},{"id":"2107.05612","title":"A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution","created":"2021-07-12","cited_by_count":91},{"id":"2202.08137","title":"A data-driven approach for learning to control computers","created":"2022-02-16","cited_by_count":88},{"id":"1909.05829","title":"Hierarchical Foresight: Self-Supervised Learning of Long-Horizon Tasks via Visual Subgoal Generation","created":"2019-09-12","cited_by_count":83},{"id":"1704.08795","title":"Mapping Instructions and Visual Observations to Actions with Reinforcement Learning","created":"2017-04-28","cited_by_count":81},{"id":"2201.12122","title":"Can Wikipedia Help Offline Reinforcement Learning?","created":"2022-01-28","cited_by_count":77},{"id":"1710.01813","title":"Neural Task Programming: Learning to Generalize Across Hierarchical Tasks","created":"2017-10-04","cited_by_count":76},{"id":"2105.03519","title":"Understanding by Understanding Not: Modeling Negation in Language Models","created":"2021-05-07","cited_by_count":73},{"id":"2011.03148","title":"RetinaGAN: An Object-aware Approach to Sim-to-Real Transfer","created":"2020-11-06","cited_by_count":70},{"id":"1807.03480","title":"Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration","created":"2018-07-10","cited_by_count":61},{"id":"1911.04577","title":"Online Replanning in Belief Space for Partially Observable Task and Motion Problems","created":"2019-11-11","cited_by_count":61},{"id":"2005.09382","title":"Human Instruction-Following with Deep Reinforcement Learning via Transfer-Learning from Text","created":"2020-05-19","cited_by_count":59},{"id":"2108.04927","title":"Embodied BERT: A Transformer Model for Embodied, Language-guided Visual Task Completion","created":"2021-08-10","cited_by_count":58},{"id":"1910.11432","title":"HRL4IN: Hierarchical Reinforcement Learning for Interactive Navigation with Mobile Manipulators","created":"2019-10-24","cited_by_count":55},{"id":"1506.04089","title":"Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences","created":"2015-06-12","cited_by_count":50},{"id":"2106.00188","title":"PIGLeT: Language Grounding Through Neuro-Symbolic Interaction in a 3D World","created":"2021-06-01","cited_by_count":47},{"id":"1705.08080","title":"Visual Semantic Planning using Deep Successor Representations","created":"2017-05-23","cited_by_count":45},{"id":"1606.02447","title":"Learning Language Games through Interaction","created":"2016-06-08","cited_by_count":43},{"id":"2107.12514","title":"Language Grounding with 3D Objects","created":"2021-07-26","cited_by_count":43},{"id":"1909.13072","title":"Regression Planning Networks","created":"2019-09-28","cited_by_count":32},{"id":"2004.06089","title":"Thinking While Moving: Deep Reinforcement Learning with Concurrent Control","created":"2020-04-13","cited_by_count":31},{"id":"2007.15543","title":"PixL2R: Guiding Reinforcement Learning Using Natural Language by Mapping Pixels to Rewards","created":"2020-07-30","cited_by_count":30},{"id":"2010.06491","title":"Broadly-Exploring, Local-Policy Trees for Long-Horizon Task Planning","created":"2020-10-13","cited_by_count":26},{"id":"2111.03189","title":"Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning","created":"2021-11-04","cited_by_count":26},{"id":"1910.09451","title":"HIGhER : Improving instruction following with Hindsight Generation for Experience Replay","created":"2019-10-21","cited_by_count":13},{"id":"2109.10312","title":"Example-Driven Model-Based Reinforcement Learning for Solving Long-Horizon Visuomotor Tasks","created":"2021-09-21","cited_by_count":13}],"next_cursor":null}