{"list":"other","total":71,"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":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"1409.3215","title":"Sequence to Sequence Learning with Neural Networks","created":"2014-09-10","cited_by_count":2986},{"id":"1904.09751","title":"The Curious Case of Neural Text Degeneration","created":"2019-04-22","cited_by_count":2916},{"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":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"1609.08144","title":"Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation","created":"2016-09-26","cited_by_count":1475},{"id":"1908.03557","title":"VisualBERT: A Simple and Performant Baseline for Vision and Language","created":"2019-08-09","cited_by_count":1296},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"1805.04833","title":"Hierarchical Neural Story Generation","created":"2018-05-13","cited_by_count":1193},{"id":"2207.05608","title":"Inner Monologue: Embodied Reasoning through Planning with Language Models","created":"2022-07-12","cited_by_count":1081},{"id":"2104.13921","title":"Open-vocabulary Object Detection via Vision and Language Knowledge Distillation","created":"2021-04-28","cited_by_count":906},{"id":"2104.12763","title":"MDETR -- Modulated Detection for End-to-End Multi-Modal Understanding","created":"2021-04-26","cited_by_count":819},{"id":"2205.06175","title":"A Generalist Agent","created":"2022-05-12","cited_by_count":808},{"id":"1912.02164","title":"Plug and Play Language Models: A Simple Approach to Controlled Text Generation","created":"2019-12-04","cited_by_count":799},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"1909.05858","title":"CTRL: A Conditional Transformer Language Model for Controllable Generation","created":"2019-09-11","cited_by_count":762},{"id":"1904.01766","title":"VideoBERT: A Joint Model for Video and Language Representation Learning","created":"2019-04-03","cited_by_count":703},{"id":"2109.12098","title":"CLIPort: What and Where Pathways for Robotic Manipulation","created":"2021-09-24","cited_by_count":622},{"id":"2209.11302","title":"ProgPrompt: Generating Situated Robot Task Plans using Large Language Models","created":"2022-09-22","cited_by_count":611},{"id":"2209.05451","title":"Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation","created":"2022-09-12","cited_by_count":551},{"id":"2202.02005","title":"BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learning","created":"2022-02-04","cited_by_count":523},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439},{"id":"2203.09509","title":"ToxiGen: A Large-Scale Machine-Generated Dataset for Adversarial and Implicit Hate Speech Detection","created":"2022-03-17","cited_by_count":422},{"id":"2009.06367","title":"GeDi: Generative Discriminator Guided Sequence Generation","created":"2020-09-14","cited_by_count":378},{"id":"2104.05218","title":"FUDGE: Controlled Text Generation With Future Discriminators","created":"2021-04-12","cited_by_count":376},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2010.14406","title":"Transporter Networks: Rearranging the Visual World for Robotic Manipulation","created":"2020-10-27","cited_by_count":344},{"id":"2106.02636","title":"MERLOT: Multimodal Neural Script Knowledge Models","created":"2021-06-04","cited_by_count":311},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305},{"id":"2306.17582","title":"ChatGPT for Robotics: Design Principles and Model Abilities","created":"2023-02-20","cited_by_count":299},{"id":"1807.04742","title":"Visual Reinforcement Learning with Imagined Goals","created":"2018-07-12","cited_by_count":251},{"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":"1906.05253","title":"Search on the Replay Buffer: Bridging Planning and Reinforcement Learning","created":"2019-06-12","cited_by_count":194},{"id":"2209.09874","title":"Open-vocabulary Queryable Scene Representations for Real World Planning","created":"2022-09-20","cited_by_count":160},{"id":"2105.06453","title":"Episodic Transformer for Vision-and-Language Navigation","created":"2021-05-13","cited_by_count":156},{"id":"2111.14447","title":"ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic","created":"2021-11-29","cited_by_count":150},{"id":"2206.11871","title":"Offline RL for Natural Language Generation with Implicit Language Q Learning","created":"2022-06-05","cited_by_count":138},{"id":"2302.05128","title":"Translating Natural Language to Planning Goals with Large-Language Models","created":"2023-02-10","cited_by_count":133},{"id":"1805.06087","title":"Learning to Write with Cooperative Discriminators","created":"2018-05-16","cited_by_count":119},{"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":"2010.02650","title":"If beam search is the answer, what was the question?","created":"2020-10-06","cited_by_count":116},{"id":"2210.01911","title":"Grounding Language with Visual Affordances over Unstructured Data","created":"2022-10-04","cited_by_count":101},{"id":"2110.01517","title":"Skill Induction and Planning with Latent Language","created":"2021-10-04","cited_by_count":99},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90},{"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":"2104.05336","title":"Machine Translation Decoding beyond Beam Search","created":"2021-04-12","cited_by_count":55},{"id":"2002.02492","title":"Consistency of a Recurrent Language Model With Respect to Incomplete Decoding","created":"2020-02-06","cited_by_count":54},{"id":"2011.08424","title":"Deep Affordance Foresight: Planning Through What Can Be Done in the Future","created":"2020-11-17","cited_by_count":41},{"id":"2204.08426","title":"CHAI: A CHatbot AI for Task-Oriented Dialogue with Offline Reinforcement Learning","created":"2022-04-18","cited_by_count":34},{"id":"1809.01215","title":"Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints","created":"2018-09-04","cited_by_count":33},{"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":"2204.10198","title":"Context-Aware Language Modeling for Goal-Oriented Dialogue Systems","created":"2022-04-18","cited_by_count":22},{"id":"2210.12250","title":"STAP: Sequencing Task-Agnostic Policies","created":"2022-10-21","cited_by_count":18},{"id":"1701.06549","title":"Learning to Decode for Future Success","created":"2017-01-23","cited_by_count":16},{"id":"2002.10375","title":"Discriminative Adversarial Search for Abstractive Summarization","created":"2020-02-24","cited_by_count":14},{"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}