{"list":"other","total":52,"rows":[{"id":"2004.06165","title":"Oscar: Object-Semantics Aligned Pre-training for Vision-Language Tasks","created":"2020-04-13","cited_by_count":1214},{"id":"2209.07753","title":"Code as Policies: Language Model Programs for Embodied Control","created":"2022-09-16","cited_by_count":1210},{"id":"2308.10848","title":"AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors","created":"2023-08-21","cited_by_count":598},{"id":"1807.06757","title":"On Evaluation of Embodied Navigation Agents","created":"2018-07-18","cited_by_count":547},{"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":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380},{"id":"2312.03275","title":"VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation","created":"2023-12-06","cited_by_count":205},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194},{"id":"2004.06799","title":"RoboTHOR: An Open Simulation-to-Real Embodied AI Platform","created":"2020-04-14","cited_by_count":193},{"id":"2402.07872","title":"PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs","created":"2024-02-12","cited_by_count":190},{"id":"1612.07182","title":"Multi-Agent Cooperation and the Emergence of (Natural) Language","created":"2016-12-21","cited_by_count":185},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178},{"id":"2202.10936","title":"A Survey of Vision-Language Pre-Trained Models","created":"2022-02-18","cited_by_count":177},{"id":"2006.02419","title":"Emergent Multi-Agent Communication in the Deep Learning Era","created":"2020-06-03","cited_by_count":170},{"id":"2309.02561","title":"Physically Grounded Vision-Language Models for Robotic Manipulation","created":"2023-09-05","cited_by_count":165},{"id":"2202.09061","title":"VLP: A Survey on Vision-Language Pre-training","created":"2022-02-18","cited_by_count":159},{"id":"2307.14535","title":"Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition","created":"2023-07-26","cited_by_count":159},{"id":"2006.00176","title":"When2com: Multi-Agent Perception via Communication Graph Grouping","created":"2020-05-30","cited_by_count":157},{"id":"1705.11192","title":"Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols","created":"2017-05-31","cited_by_count":125},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110},{"id":"2309.15943","title":"Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?","created":"2023-09-27","cited_by_count":106},{"id":"2312.08782","title":"Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis","created":"2023-12-14","cited_by_count":103},{"id":"1804.03984","title":"Emergence of Linguistic Communication from Referential Games with Symbolic and Pixel Input","created":"2018-04-11","cited_by_count":102},{"id":"2103.16544","title":"Visual Room Rearrangement","created":"2021-03-30","cited_by_count":102},{"id":"2310.10103","title":"Navigation with Large Language Models: Semantic Guesswork as a Heuristic for Planning","created":"2023-10-16","cited_by_count":89},{"id":"2311.06430","title":"GOAT: GO to Any Thing","created":"2023-11-10","cited_by_count":89},{"id":"1706.08502","title":"Natural Language Does Not Emerge 'Naturally' in Multi-Agent Dialog","created":"2017-06-26","cited_by_count":86},{"id":"2310.10021","title":"Bootstrap Your Own Skills: Learning to Solve New Tasks with Large Language Model Guidance","created":"2023-10-16","cited_by_count":86},{"id":"2403.12482","title":"Embodied LLM Agents Learn to Cooperate in Organized Teams","created":"2024-03-19","cited_by_count":82},{"id":"2309.10309","title":"Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skill","created":"2023-09-19","cited_by_count":77},{"id":"2303.03480","title":"Can an Embodied Agent Find Your \"Cat-shaped Mug\"? LLM-Guided Exploration for Zero-Shot Object Navigation","created":"2023-03-06","cited_by_count":74},{"id":"2402.10670","title":"OpenFMNav: Towards Open-Set Zero-Shot Object Navigation via Vision-Language Foundation Models","created":"2024-02-16","cited_by_count":67},{"id":"2005.07064","title":"Multi-agent Communication meets Natural Language: Synergies between Functional and Structural Language Learning","created":"2020-05-14","cited_by_count":66},{"id":"2406.10279","title":"We Have a Package for You! A Comprehensive Analysis of Package Hallucinations by Code Generating LLMs","created":"2024-06-12","cited_by_count":65},{"id":"2401.02695","title":"VoroNav: Voronoi-based Zero-shot Object Navigation with Large Language Model","created":"2024-01-05","cited_by_count":57},{"id":"2211.16649","title":"CLIP-Nav: Using CLIP for Zero-Shot Vision-and-Language Navigation","created":"2022-11-30","cited_by_count":55},{"id":"2406.02537","title":"TopViewRS: Vision-Language Models as Top-View Spatial Reasoners","created":"2024-06-04","cited_by_count":49},{"id":"2310.07889","title":"LangNav: Language as a Perceptual Representation for Navigation","created":"2023-10-11","cited_by_count":47},{"id":"2403.15637","title":"CoNVOI: Context-aware Navigation using Vision Language Models in Outdoor and Indoor Environments","created":"2024-03-22","cited_by_count":43},{"id":"2310.15127","title":"Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models","created":"2023-10-23","cited_by_count":37},{"id":"2109.05413","title":"Learning Selective Communication for Multi-Agent Path Finding","created":"2021-09-12","cited_by_count":32},{"id":"2403.15223","title":"TriHelper: Zero-Shot Object Navigation with Dynamic Assistance","created":"2024-03-22","cited_by_count":25},{"id":"2110.05769","title":"Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents","created":"2021-10-12","cited_by_count":19},{"id":"2105.08601","title":"Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection","created":"2021-05-18","cited_by_count":14},{"id":"2309.10103","title":"Reasoning about the Unseen for Efficient Outdoor Object Navigation","created":"2023-09-18","cited_by_count":13},{"id":"2003.11675","title":"Risk-Aware Planning and Assignment for Ground Vehicles using Uncertain Perception from Aerial Vehicles","created":"2020-03-25","cited_by_count":12},{"id":"2304.09448","title":"EC^2: Emergent Communication for Embodied Control","created":"2023-04-19","cited_by_count":10},{"id":"2405.05363","title":"LOC-ZSON: Language-driven Object-Centric Zero-Shot Object Retrieval and Navigation","created":"2024-05-08","cited_by_count":8},{"id":"2402.19007","title":"DOZE: A Dataset for Open-Vocabulary Zero-Shot Object Navigation in Dynamic Environments","created":"2024-02-29","cited_by_count":4},{"id":"2310.07621","title":"AG-CVG: Coverage Planning with a Mobile Recharging UGV and an Energy-Constrained UAV","created":"2023-10-11","cited_by_count":3},{"id":"2401.12624","title":"Knowledge Distillation from Language-Oriented to Emergent Communication for Multi-Agent Remote Control","created":"2024-01-23","cited_by_count":3},{"id":"2209.06415","title":"DMCA: Dense Multi-agent Navigation using Attention and Communication","created":"2022-09-14","cited_by_count":1}],"next_cursor":null}