{"total":83,"rows":[{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228,"area":null},{"id":"2202.01771","title":"Pre-Trained Language Models for Interactive Decision-Making","created":"2022-02-03","cited_by_count":221,"area":null},{"id":"2309.09971","title":"MindAgent: Emergent Gaming Interaction","created":"2023-09-18","cited_by_count":88,"area":null},{"id":"2401.08743","title":"MMToM-QA: Multimodal Theory of Mind Question Answering","created":"2024-01-16","cited_by_count":85,"area":null},{"id":"2408.03943","title":"Building Machines that Learn and Think with People","created":"2024-07-22","cited_by_count":73,"area":null},{"id":"2103.14025","title":"The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AI","created":"2021-03-25","cited_by_count":65,"area":null},{"id":"2111.09189","title":"ToM2C: Target-oriented Multi-agent Communication and Cooperation with Theory of Mind","created":"2021-10-15","cited_by_count":58,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2102.12321","title":"AGENT: A Benchmark for Core Psychological Reasoning","created":"2021-02-24","cited_by_count":42,"area":null},{"id":"2303.17592","title":"Learning Human-to-Robot Handovers from Point Clouds","created":"2023-03-30","cited_by_count":34,"area":null},{"id":"2305.13246","title":"Interactive Natural Language Processing","created":"2023-05-22","cited_by_count":31,"area":null},{"id":"2405.10313","title":"How Far Are We From AGI: Are LLMs All We Need?","created":"2024-05-16","cited_by_count":31,"area":null},{"id":"2402.17930","title":"Pragmatic Instruction Following and Goal Assistance via Cooperative Language-Guided Inverse Planning","created":"2024-02-27","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2211.11746","title":"Last-Mile Embodied Visual Navigation","created":"2022-11-21","cited_by_count":25,"area":null},{"id":"2106.11650","title":"A Survey on Human-aware Robot Navigation","created":"2021-06-22","cited_by_count":24,"area":null},{"id":"2301.05223","title":"NOPA: Neurally-guided Online Probabilistic Assistance for Building Socially Intelligent Home Assistants","created":"2023-01-12","cited_by_count":23,"area":null},{"id":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2412.05255","title":"TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft","created":"2024-12-06","cited_by_count":21,"area":null},{"id":"2310.03779","title":"HandMeThat: Human-Robot Communication in Physical and Social Environments","created":"2023-10-05","cited_by_count":20,"area":null},{"id":"2211.15501","title":"Proactive Robot Assistance via Spatio-Temporal Object Modeling","created":"2022-11-28","cited_by_count":18,"area":null},{"id":"2403.11075","title":"GOMA: Proactive Embodied Cooperative Communication via Goal-Oriented Mental Alignment","created":"2024-03-17","cited_by_count":16,"area":null},{"id":"2205.09747","title":"HandoverSim: A Simulation Framework and Benchmark for Human-to-Robot Object Handovers","created":"2022-05-19","cited_by_count":15,"area":null},{"id":"2304.13269","title":"Games for Artificial Intelligence Research: A Review and Perspectives","created":"2023-04-26","cited_by_count":14,"area":null},{"id":"2306.00087","title":"Adaptive Coordination in Social Embodied Rearrangement","created":"2023-05-31","cited_by_count":14,"area":null},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13,"area":null},{"id":"2410.14682","title":"ET-Plan-Bench: Embodied Task-level Planning Benchmark Towards Spatial-Temporal Cognition with Foundation Models","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2411.01796","title":"Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge","created":"2024-11-04","cited_by_count":13,"area":null},{"id":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2506.19806","title":"LLM-Based Social Simulations Require a Boundary","created":"2025-06-24","cited_by_count":12,"area":null},{"id":"2404.09001","title":"Smart Help: Strategic Opponent Modeling for Proactive and Adaptive Robot Assistance in Households","created":"2024-04-13","cited_by_count":11,"area":null},{"id":"2111.14422","title":"Agent-Centric Relation Graph for Object Visual Navigation","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2409.18073","title":"Infer Human's Intentions Before Following Natural Language Instructions","created":"2024-09-26","cited_by_count":10,"area":null},{"id":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2211.01602","title":"Optimal Behavior Prior: Data-Efficient Human Models for Improved Human-AI Collaboration","created":"2022-11-03","cited_by_count":8,"area":null},{"id":"2107.00956","title":"SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents","created":"2021-07-02","cited_by_count":7,"area":null},{"id":"2604.07774","title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","created":"2026-04-09","cited_by_count":7,"area":null},{"id":"2203.08141","title":"Object Manipulation via Visual Target Localization","created":"2022-03-15","cited_by_count":6,"area":null},{"id":"2407.06762","title":"Explicit Modelling of Theory of Mind for Belief Prediction in Nonverbal Social Interactions","created":"2024-07-09","cited_by_count":6,"area":null},{"id":"2409.10849","title":"Pragmatic Embodied Spoken Instruction Following in Human-Robot Collaboration with Theory of Mind","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2204.09047","title":"Learning Theory of Mind via Dynamic Traits Attribution","created":"2022-04-17","cited_by_count":5,"area":null},{"id":"2402.07402","title":"BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind","created":"2024-02-12","cited_by_count":5,"area":null},{"id":"2404.07347","title":"Gaze-Guided Graph Neural Network for Action Anticipation Conditioned on Intention","created":"2024-04-10","cited_by_count":5,"area":null},{"id":"2208.13626","title":"CH-MARL: A Multimodal Benchmark for Cooperative, Heterogeneous Multi-Agent Reinforcement Learning","created":"2022-08-26","cited_by_count":4,"area":null},{"id":"2410.01440","title":"Closed-Loop Long-Horizon Robotic Planning via Equilibrium Sequence Modeling","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2411.04987","title":"Few-Shot Task Learning through Inverse Generative Modeling","created":"2024-11-07","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2602.06139","title":"EgoAVU: Egocentric Audio-Visual Understanding","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2103.14712","title":"Generating and Evaluating Explanations of Attended and Error-Inducing Input Regions for VQA Models","created":"2021-03-26","cited_by_count":2,"area":null},{"id":"2407.20642","title":"Effectively Leveraging CLIP for Generating Situational Summaries of Images and Videos","created":"2024-07-30","cited_by_count":2,"area":null},{"id":"2503.12974","title":"Exploring 3D Reasoning-Driven Planning: From Implicit Human Intentions to Route-Aware Activity Planning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2503.16545","title":"EmpathyAgent: Can Embodied Agents Conduct Empathetic Actions?","created":"2025-03-19","cited_by_count":2,"area":null},{"id":"2604.08509","title":"Visually-grounded Humanoid Agents","created":"2026-04-09","cited_by_count":2,"area":null},{"id":"2605.11688","title":"Shaping Zero-Shot Coordination via State Blocking","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2201.08520","title":"Learning Two-Step Hybrid Policy for Graph-Based Interpretable Reinforcement Learning","created":"2022-01-21","cited_by_count":1,"area":null},{"id":"2205.06483","title":"Modeling Human Behavior Part II -- Cognitive approaches and Uncertainty","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2205.06485","title":"Modeling Human Behavior Part I -- Learning and Belief Approaches","created":"2022-05-13","cited_by_count":1,"area":null},{"id":"2303.13489","title":"Boosting Reinforcement Learning and Planning with Demonstrations: A Survey","created":"2023-03-23","cited_by_count":1,"area":null},{"id":"2305.06485","title":"Multimodal Contextualized Plan Prediction for Embodied Task Completion","created":"2023-05-10","cited_by_count":1,"area":null},{"id":"2503.00248","title":"Human-AI Collaboration: Trade-offs Between Performance and Preferences","created":"2025-02-28","cited_by_count":1,"area":null},{"id":"2506.01312","title":"Growing Through Experience: Scaling Episodic Grounding in Language Models","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2509.05091","title":"ProToM: Promoting Prosocial Behaviour via Theory of Mind-Informed Feedback","created":"2025-09-05","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2604.17019","title":"Mini-BEHAVIOR-Gran: Revealing U-Shaped Effects of Instruction Granularity on Language-Guided Embodied Agents","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2112.08093","title":"Towards Controllable Agent in MOBA Games with Generative Modeling","created":"2021-12-15","cited_by_count":0,"area":null},{"id":"2207.09619","title":"Learning Latent Traits for Simulated Cooperative Driving Tasks","created":"2022-07-20","cited_by_count":0,"area":null},{"id":"2210.15908","title":"Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport","created":"2022-10-28","cited_by_count":0,"area":null},{"id":"2303.11425","title":"Improving Human-Robot Collaboration via Computational Design","created":"2023-03-20","cited_by_count":0,"area":null},{"id":"2310.18303","title":"Socially Cognizant Robotics for a Technology Enhanced Society","created":"2023-10-27","cited_by_count":0,"area":null},{"id":"2311.02602","title":"Get the Ball Rolling: Alerting Autonomous Robots When to Help to Close the Healthcare Loop","created":"2023-11-05","cited_by_count":0,"area":null},{"id":"2504.07597","title":"Learning Long Short-Term Intention within Human Daily Behaviors","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2507.14088","title":"DPMT: Dual Process Multi-scale Theory of Mind Framework for Real-time Human-AI Collaboration","created":"2025-07-18","cited_by_count":0,"area":null},{"id":"2507.18623","title":"Moving Out: Physically-grounded Human-AI Collaboration","created":"2025-07-24","cited_by_count":0,"area":null},{"id":"2512.04107","title":"Rethinking AI Evaluation in Education: The TEACH-AI Framework and Benchmark for Generative AI Assistants","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2512.19992","title":"S$^3$IT: A Benchmark for Spatially Situated Social Intelligence Test","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2605.27394","title":"Human-AI Collaboration for Estimating Scientific Replicability","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2607.06691","title":"CoMind: Understanding Collaborative Human Activity from Multiple Minds and Views","created":"2026-07-07","cited_by_count":0,"area":null},{"id":"2607.18062","title":"UniETP: Unifying Environments for Generalizable Embodied Task Planning","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.22149","title":"Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic Constraints","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2609.05596","title":"Time-Aware Assistive Navigation","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.28910","title":"Robots That Take Initiative: A Framework for Building and Evaluating Proactive Robots","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.02170","title":"Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17694","title":"HelpMeOut: A Neuropsychology-Grounded Benchmark for Error-Aware Monitoring of Household Task Execution","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}