{"list":"other","total":56,"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":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2110.14168","title":"Training Verifiers to Solve Math Word Problems","created":"2021-10-27","cited_by_count":10109},{"id":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2205.01068","title":"OPT: Open Pre-trained Transformer Language Models","created":"2022-05-02","cited_by_count":3512},{"id":"2204.01691","title":"Do As I Can, Not As I Say: Grounding Language in Robotic Affordances","created":"2022-04-04","cited_by_count":2348},{"id":"1908.02265","title":"ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks","created":"2019-08-06","cited_by_count":2222},{"id":"1909.01066","title":"Language Models as Knowledge Bases?","created":"2019-09-03","cited_by_count":1936},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"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":"1911.12543","title":"How Can We Know What Language Models Know?","created":"2019-11-28","cited_by_count":959},{"id":"2002.08910","title":"How Much Knowledge Can You Pack Into the Parameters of a Language Model?","created":"2020-02-10","cited_by_count":719},{"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":"2106.13884","title":"Multimodal Few-Shot Learning with Frozen Language Models","created":"2021-06-25","cited_by_count":661},{"id":"1806.07011","title":"VirtualHome: Simulating Household Activities via Programs","created":"2018-06-19","cited_by_count":415},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"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":"2005.07648","title":"Language Conditioned Imitation Learning over Unstructured Data","created":"2020-05-15","cited_by_count":209},{"id":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"1909.00505","title":"Commonsense Knowledge Mining from Pretrained Models","created":"2019-09-02","cited_by_count":189},{"id":"2106.00737","title":"Implicit Representations of Meaning in Neural Language Models","created":"2021-06-01","cited_by_count":180},{"id":"2103.05247","title":"Pretrained Transformers as Universal Computation Engines","created":"2021-03-09","cited_by_count":162},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"1906.07343","title":"Language as an Abstraction for Hierarchical Deep Reinforcement Learning","created":"2019-06-18","cited_by_count":138},{"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":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"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":"2109.03034","title":"Generate & Rank: A Multi-task Framework for Math Word Problems","created":"2021-09-07","cited_by_count":82},{"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":"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":"2003.01200","title":"Natural Language Processing Advancements By Deep Learning: A Survey","created":"2020-03-02","cited_by_count":50},{"id":"2008.07792","title":"ReLMoGen: Leveraging Motion Generation in Reinforcement Learning for Mobile Manipulation","created":"2020-08-18","cited_by_count":49},{"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":"1909.13072","title":"Regression Planning Networks","created":"2019-09-28","cited_by_count":32},{"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":"1904.12907","title":"Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning","created":"2019-04-29","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},{"id":"2005.00619","title":"Probing Contextual Language Models for Common Ground with Visual Representations","created":"2020-05-01","cited_by_count":9}],"next_cursor":null}