{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.11401","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","created":"2020-05-22","cited_by_count":9297},{"id":"2501.12948","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","created":"2025-01-22","cited_by_count":6330},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2303.11366","title":"Reflexion: Language Agents with Verbal Reinforcement Learning","created":"2023-03-20","cited_by_count":4276},{"id":"2304.03442","title":"Generative Agents: Interactive Simulacra of Human Behavior","created":"2023-04-07","cited_by_count":3568},{"id":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"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":"2305.16291","title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","created":"2023-05-25","cited_by_count":2191},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"1706.02275","title":"Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments","created":"2017-06-07","cited_by_count":1558},{"id":"2303.17760","title":"CAMEL: Communicative Agents for \"Mind\" Exploration of Large Language Model Society","created":"2023-03-31","cited_by_count":1395},{"id":"2310.08560","title":"MemGPT: Towards LLMs as Operating Systems","created":"2023-10-12","cited_by_count":1389},{"id":"2112.04426","title":"Improving language models by retrieving from trillions of tokens","created":"2021-12-08","cited_by_count":1293},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2307.05973","title":"VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models","created":"2023-07-12","cited_by_count":750},{"id":"2312.08914","title":"CogAgent: A Visual Language Model for GUI Agents","created":"2023-12-14","cited_by_count":704},{"id":"1902.04043","title":"The StarCraft Multi-Agent Challenge","created":"2019-02-11","cited_by_count":597},{"id":"2007.00643","title":"Object Goal Navigation using Goal-Oriented Semantic Exploration","created":"2020-07-01","cited_by_count":429},{"id":"2309.02427","title":"Cognitive Architectures for Language Agents","created":"2023-09-05","cited_by_count":429},{"id":"2310.11667","title":"SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents","created":"2023-10-18","cited_by_count":367},{"id":"2210.05714","title":"Visual Language Maps for Robot Navigation","created":"2022-10-11","cited_by_count":365},{"id":"2309.16650","title":"ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planning","created":"2023-09-28","cited_by_count":365},{"id":"1410.3916","title":"Memory Networks","created":"2014-10-15","cited_by_count":363},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353},{"id":"1910.05789","title":"On the Utility of Learning about Humans for Human-AI Coordination","created":"2019-10-13","cited_by_count":349},{"id":"1909.07528","title":"Emergent Tool Use From Multi-Agent Autocurricula","created":"2019-09-17","cited_by_count":313},{"id":"2307.06135","title":"SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planning","created":"2023-07-12","cited_by_count":294},{"id":"2405.14831","title":"HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models","created":"2024-05-23","cited_by_count":281},{"id":"1807.01281","title":"Human-level performance in first-person multiplayer games with population-based deep reinforcement learning","created":"2018-07-03","cited_by_count":264},{"id":"2007.04954","title":"ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation","created":"2020-07-09","cited_by_count":250},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"1902.00506","title":"The Hanabi Challenge: A New Frontier for AI Research","created":"2019-02-01","cited_by_count":197},{"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":"2201.13360","title":"Hydra: A Real-time Spatial Perception System for 3D Scene Graph Construction and Optimization","created":"2022-01-31","cited_by_count":178},{"id":"2501.00309","title":"Retrieval-Augmented Generation with Graphs (GraphRAG)","created":"2024-12-31","cited_by_count":172},{"id":"2210.05663","title":"CLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory","created":"2022-10-11","cited_by_count":165},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2205.14953","title":"Multi-Agent Reinforcement Learning is a Sequence Modeling Problem","created":"2022-05-30","cited_by_count":155},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150},{"id":"2010.09890","title":"Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration","created":"2020-10-19","cited_by_count":133},{"id":"2211.12561","title":"Retrieval-Augmented Multimodal Language Modeling","created":"2022-11-22","cited_by_count":125},{"id":"2110.07342","title":"FILM: Following Instructions in Language with Modular Methods","created":"2021-10-12","cited_by_count":121},{"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":"2501.13958","title":"A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models","created":"2025-01-21","cited_by_count":88},{"id":"2408.03615","title":"Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks","created":"2024-08-07","cited_by_count":84},{"id":"2404.13696","title":"Clio: Real-time Task-Driven Open-Set 3D Scene Graphs","created":"2024-04-21","cited_by_count":81},{"id":"2305.16960","title":"Training Socially Aligned Language Models on Simulated Social Interactions","created":"2023-05-26","cited_by_count":78},{"id":"2310.15200","title":"Open-Set Image Tagging with Multi-Grained Text Supervision","created":"2023-10-23","cited_by_count":67},{"id":"2007.04979","title":"A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks","created":"2020-07-09","cited_by_count":52},{"id":"2403.13679","title":"SocialBench: Sociality Evaluation of Role-Playing Conversational Agents","created":"2024-03-20","cited_by_count":50},{"id":"1903.00784","title":"Neural MMO: A Massively Multiagent Game Environment for Training and Evaluating Intelligent Agents","created":"2019-03-02","cited_by_count":44},{"id":"2203.17251","title":"Continuous Scene Representations for Embodied AI","created":"2022-03-31","cited_by_count":39},{"id":"2405.14744","title":"Exploring Prosocial Irrationality for LLM Agents: A Social Cognition View","created":"2024-05-23","cited_by_count":38},{"id":"1405.6341","title":"Efficient Model Learning for Human-Robot Collaborative Tasks","created":"2014-05-24","cited_by_count":35},{"id":"2410.15665","title":"Long Term Memory: The Foundation of AI Self-Evolution","created":"2024-10-21","cited_by_count":30},{"id":"2406.12203","title":"InterIntent: Investigating Social Intelligence of LLMs via Intention Understanding in an Interactive Game Context","created":"2024-06-18","cited_by_count":26},{"id":"2009.04300","title":"SEAN: Social Environment for Autonomous Navigation","created":"2020-09-09","cited_by_count":18},{"id":"2305.17537","title":"Modeling Dynamic Environments with Scene Graph Memory","created":"2023-05-27","cited_by_count":18},{"id":"2403.19267","title":"MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs","created":"2024-03-28","cited_by_count":18},{"id":"2107.02907","title":"Learning Latent Actions to Control Assistive Robots","created":"2021-07-06","cited_by_count":17},{"id":"2112.04063","title":"Semantic OcTree Mapping and Shannon Mutual Information Computation for Robot Exploration","created":"2021-12-08","cited_by_count":16},{"id":"2406.14373","title":"Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory","created":"2024-06-20","cited_by_count":16},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14},{"id":"2303.03178","title":"A System for Generalized 3D Multi-Object Search","created":"2023-03-06","cited_by_count":9}],"next_cursor":null}