{"total":58,"rows":[{"id":"2304.08354","title":"Tool Learning with Foundation Models","created":"2023-04-17","cited_by_count":302,"area":"agents"},{"id":"2103.04918","title":"A Survey of Embodied AI: From Simulators to Research Tasks","created":"2021-03-08","cited_by_count":261,"area":null},{"id":"2301.06015","title":"Diffusion-based Generation, Optimization, and Planning in 3D Scenes","created":"2023-01-15","cited_by_count":239,"area":"diffusion"},{"id":"2304.08488","title":"Affordances from Human Videos as a Versatile Representation for Robotics","created":"2023-04-17","cited_by_count":226,"area":null},{"id":"2307.07162","title":"Drive Like a Human: Rethinking Autonomous Driving with Large Language Models","created":"2023-07-14","cited_by_count":160,"area":"lr"},{"id":"2201.10029","title":"PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning","created":"2022-01-25","cited_by_count":150,"area":null},{"id":"2204.03514","title":"Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scale","created":"2022-04-07","cited_by_count":117,"area":"offlinerl"},{"id":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2203.09905","title":"Learning Affordance Grounding from Exocentric Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2106.14440","title":"VAT-Mart: Learning Visual Action Trajectory Proposals for Manipulating 3D ARTiculated Objects","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2104.04112","title":"Auxiliary Tasks and Exploration Enable ObjectNav","created":"2021-04-08","cited_by_count":74,"area":null},{"id":"2310.08588","title":"Octopus: Embodied Vision-Language Programmer from Environmental Feedback","created":"2023-10-12","cited_by_count":73,"area":"mllm"},{"id":"2308.04758","title":"Bird's-Eye-View Scene Graph for Vision-Language Navigation","created":"2023-08-09","cited_by_count":72,"area":null},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2108.03658","title":"One-Shot Object Affordance Detection in the Wild","created":"2021-08-08","cited_by_count":40,"area":null},{"id":"2110.05734","title":"Learning Efficient Multi-Agent Cooperative Visual Exploration","created":"2021-10-12","cited_by_count":19,"area":null},{"id":"2110.07692","title":"Shaping embodied agent behavior with activity-context priors from egocentric video","created":"2021-10-14","cited_by_count":17,"area":null},{"id":"2311.13793","title":"Evidential Active Recognition: Intelligent and Prudent Open-World Embodied Perception","created":"2023-11-23","cited_by_count":15,"area":null},{"id":"2502.04981","title":"AutoOcc: Automatic Open-Ended Semantic Occupancy Annotation via Vision-Language Guided Gaussian Splatting","created":"2025-02-07","cited_by_count":14,"area":"mllm"},{"id":"2303.06457","title":"Active Visual Exploration Based on Attention-Map Entropy","created":"2023-03-11","cited_by_count":13,"area":null},{"id":"2402.04519","title":"BioDrone: A Bionic Drone-based Single Object Tracking Benchmark for Robust Vision","created":"2024-02-07","cited_by_count":13,"area":null},{"id":"2102.02337","title":"Environment Predictive Coding for Embodied Agents","created":"2021-02-03","cited_by_count":12,"area":null},{"id":"2304.03696","title":"MOPA: Modular Object Navigation with PointGoal Agents","created":"2023-04-07","cited_by_count":11,"area":null},{"id":"2204.07414","title":"SOTVerse: A User-defined Task Space of Single Object Tracking","created":"2022-04-15","cited_by_count":10,"area":null},{"id":"2304.11241","title":"AutoNeRF: Training Implicit Scene Representations with Autonomous Agents","created":"2023-04-21","cited_by_count":10,"area":null},{"id":"2109.08521","title":"Focus on Impact: Indoor Exploration with Intrinsic Motivation","created":"2021-09-14","cited_by_count":9,"area":null},{"id":"2112.05298","title":"IFR-Explore: Learning Inter-object Functional Relationships in 3D Indoor Scenes","created":"2021-12-10","cited_by_count":9,"area":null},{"id":"2311.03357","title":"Exploitation-Guided Exploration for Semantic Embodied Navigation","created":"2023-11-06","cited_by_count":9,"area":null},{"id":"2401.07770","title":"Seeing the Unseen: Visual Common Sense for Semantic Placement","created":"2024-01-15","cited_by_count":9,"area":null},{"id":"2105.05873","title":"Out of the Box: Embodied Navigation in the Real World","created":"2021-05-12","cited_by_count":8,"area":null},{"id":"2201.09862","title":"Learning to Act with Affordance-Aware Multimodal Neural SLAM","created":"2022-01-24","cited_by_count":8,"area":null},{"id":"2203.12299","title":"NavDreams: Towards Camera-Only RL Navigation Among Humans","created":"2022-03-23","cited_by_count":8,"area":null},{"id":"2401.13362","title":"TraKDis: A Transformer-based Knowledge Distillation Approach for Visual Reinforcement Learning with Application to Cloth Manipulation","created":"2024-01-24","cited_by_count":8,"area":"deeprl"},{"id":"2402.03824","title":"A call for embodied AI","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2404.03482","title":"AdaGlimpse: Active Visual Exploration with Arbitrary Glimpse Position and Scale","created":"2024-04-04","cited_by_count":7,"area":"deeprl"},{"id":"2203.04516","title":"Update Compression for Deep Neural Networks on the Edge","created":"2022-03-09","cited_by_count":6,"area":null},{"id":"2301.07150","title":"Embodied Agents for Efficient Exploration and Smart Scene Description","created":"2023-01-17","cited_by_count":6,"area":null},{"id":"2111.05448","title":"Towards Active Vision for Action Localization with Reactive Control and Predictive Learning","created":"2021-11-09","cited_by_count":5,"area":null},{"id":"2204.08502","title":"Spot the Difference: A Novel Task for Embodied Agents in Changing Environments","created":"2022-04-18","cited_by_count":5,"area":null},{"id":"2211.07898","title":"Learning-Augmented Model-Based Planning for Visual Exploration","created":"2022-11-15","cited_by_count":5,"area":null},{"id":"2203.06671","title":"Summarizing a virtual robot's past actions in natural language","created":"2022-03-13","cited_by_count":3,"area":null},{"id":"2206.10606","title":"Good Time to Ask: A Learning Framework for Asking for Help in Embodied Visual Navigation","created":"2022-06-20","cited_by_count":3,"area":null},{"id":"2204.09069","title":"Embodied Navigation at the Art Gallery","created":"2022-04-19","cited_by_count":2,"area":null},{"id":"2211.10934","title":"Active Exploration based on Information Gain by Particle Filter for Efficient Spatial Concept Formation","created":"2022-11-20","cited_by_count":2,"area":null},{"id":"2302.03566","title":"Look Around and Learn: Self-Training Object Detection by Exploration","created":"2023-02-07","cited_by_count":2,"area":null},{"id":"2311.15335","title":"TORE: Token Recycling in Vision Transformers for Efficient Active Visual Exploration","created":"2023-11-26","cited_by_count":2,"area":null},{"id":"2404.16216","title":"ActiveRIR: Active Audio-Visual Exploration for Acoustic Environment Modeling","created":"2024-04-24","cited_by_count":2,"area":null},{"id":"2510.19766","title":"SEA: Semantic Map Prediction for Active Exploration of Uncertain Areas","created":"2025-10-22","cited_by_count":2,"area":"deeprl"},{"id":"2604.02829","title":"STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2111.01364","title":"Learning to Explore by Reinforcement over High-Level Options","created":"2021-11-02","cited_by_count":1,"area":null},{"id":"2112.09515","title":"Symmetry-aware Neural Architecture for Embodied Visual Navigation","created":"2021-12-17","cited_by_count":1,"area":null},{"id":"2301.09854","title":"Effective Baselines for Multiple Object Rearrangement Planning in Partially Observable Mapped Environments","created":"2023-01-24","cited_by_count":1,"area":null},{"id":"2306.13760","title":"Task-Driven Graph Attention for Hierarchical Relational Object Navigation","created":"2023-06-23","cited_by_count":1,"area":null},{"id":"2311.00252","title":"Active Neural Topological Mapping for Multi-Agent Exploration","created":"2023-11-01","cited_by_count":1,"area":null},{"id":"2112.14084","title":"Embodied Learning for Lifelong Visual Perception","created":"2021-12-28","cited_by_count":0,"area":null},{"id":"2310.06164","title":"DEUX: Active Exploration for Learning Unsupervised Depth Perception","created":"2023-09-16","cited_by_count":0,"area":null},{"id":"2405.11298","title":"Visual Episodic Memory-based Exploration","created":"2024-05-18","cited_by_count":0,"area":"deeprl"},{"id":"2405.15222","title":"Leveraging Unknown Objects to Construct Labeled-Unlabeled Meta-Relationships for Zero-Shot Object Navigation","created":"2024-05-24","cited_by_count":0,"area":null}],"next_cursor":null}