{"total":85,"rows":[{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2112.10482","title":"ScanQA: 3D Question Answering for Spatial Scene Understanding","created":"2021-12-20","cited_by_count":346,"area":null},{"id":"2107.14483","title":"ManiSkill: Generalizable Manipulation Skill Benchmark with Large-Scale Demonstrations","created":"2021-07-30","cited_by_count":197,"area":null},{"id":"2407.06886","title":"Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI","created":"2024-07-09","cited_by_count":179,"area":null},{"id":"2203.02764","title":"Bridging the Gap Between Learning in Discrete and Continuous Environments for Vision-and-Language Navigation","created":"2022-03-05","cited_by_count":132,"area":null},{"id":"2103.17138","title":"SOON: Scenario Oriented Object Navigation with Graph-based Exploration","created":"2021-03-31","cited_by_count":119,"area":null},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117,"area":null},{"id":"2110.05122","title":"Pano-AVQA: Grounded Audio-Visual Question Answering on 360$^\\circ$ Videos","created":"2021-10-11","cited_by_count":86,"area":null},{"id":"2106.07876","title":"Vision-Language Navigation with Random Environmental Mixup","created":"2021-06-15","cited_by_count":70,"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":"2106.15648","title":"Learning to Map for Active Semantic Goal Navigation","created":"2021-06-29","cited_by_count":50,"area":null},{"id":"2103.12944","title":"Scene-Intuitive Agent for Remote Embodied Visual Grounding","created":"2021-03-24","cited_by_count":49,"area":null},{"id":"2105.08710","title":"Fast and Slow Learning of Recurrent Independent Mechanisms","created":"2021-05-18","cited_by_count":36,"area":null},{"id":"2103.04564","title":"Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomization","created":"2021-03-08","cited_by_count":35,"area":null},{"id":"2108.11544","title":"Vision-Language Navigation: A Survey and Taxonomy","created":"2021-08-26","cited_by_count":34,"area":null},{"id":"2401.12975","title":"HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments","created":"2024-01-23","cited_by_count":32,"area":null},{"id":"2106.03805","title":"3DB: A Framework for Debugging Computer Vision Models","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2103.05423","title":"Deep Learning Based 3D Segmentation: A Survey","created":"2021-03-09","cited_by_count":30,"area":null},{"id":"2106.13948","title":"Core Challenges in Embodied Vision-Language Planning","created":"2021-06-26","cited_by_count":30,"area":null},{"id":"2205.01551","title":"Cross-View Cross-Scene Multi-View Crowd Counting","created":"2022-05-03","cited_by_count":28,"area":null},{"id":"2108.11550","title":"The Surprising Effectiveness of Visual Odometry Techniques for Embodied PointGoal Navigation","created":"2021-08-26","cited_by_count":27,"area":null},{"id":"2106.00596","title":"Look Wide and Interpret Twice: Improving Performance on Interactive Instruction-following Tasks","created":"2021-06-01","cited_by_count":26,"area":null},{"id":"2210.16822","title":"Towards Versatile Embodied Navigation","created":"2022-10-30","cited_by_count":26,"area":null},{"id":"2401.11067","title":"Make-A-Shape: a Ten-Million-scale 3D Shape Model","created":"2024-01-20","cited_by_count":25,"area":null},{"id":"2412.20977","title":"UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI","created":"2024-12-30","cited_by_count":25,"area":null},{"id":"2209.11972","title":"Ground then Navigate: Language-guided Navigation in Dynamic Scenes","created":"2022-09-24","cited_by_count":20,"area":null},{"id":"2406.19236","title":"Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions","created":"2024-06-27","cited_by_count":19,"area":null},{"id":"2107.01151","title":"Collaborative Visual Navigation","created":"2021-07-02","cited_by_count":18,"area":null},{"id":"2108.03803","title":"Mis-spoke or mis-lead: Achieving Robustness in Multi-Agent Communicative Reinforcement Learning","created":"2021-08-09","cited_by_count":18,"area":null},{"id":"2204.04421","title":"Unbiased Directed Object Attention Graph for Object Navigation","created":"2022-04-09","cited_by_count":18,"area":null},{"id":"2303.04077","title":"Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation Using Scene Object Spectrum Grounding","created":"2023-03-07","cited_by_count":18,"area":null},{"id":"2303.15440","title":"EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision","created":"2023-03-27","cited_by_count":18,"area":null},{"id":"2107.04132","title":"A Systematic Survey of Text Worlds as Embodied Natural Language Environments","created":"2021-07-08","cited_by_count":17,"area":null},{"id":"2202.03735","title":"Navigating to Objects in Unseen Environments by Distance Prediction","created":"2022-02-08","cited_by_count":16,"area":null},{"id":"2107.11252","title":"Adversarial Reinforced Instruction Attacker for Robust Vision-Language Navigation","created":"2021-07-23","cited_by_count":15,"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":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2210.02075","title":"On the Learning Mechanisms in Physical Reasoning","created":"2022-10-05","cited_by_count":11,"area":null},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2407.17398","title":"3D Question Answering for City Scene Understanding","created":"2024-07-24","cited_by_count":10,"area":null},{"id":"2402.14304","title":"Vision-Language Navigation with Embodied Intelligence: A Survey","created":"2024-02-22","cited_by_count":9,"area":null},{"id":"2405.16559","title":"Map-based Modular Approach for Zero-shot Embodied Question Answering","created":"2024-05-26","cited_by_count":9,"area":null},{"id":"2103.01350","title":"Hierarchical and Partially Observable Goal-driven Policy Learning with Goals Relational Graph","created":"2021-03-01","cited_by_count":7,"area":null},{"id":"2108.02846","title":"Communicative Learning with Natural Gestures for Embodied Navigation Agents with Human-in-the-Scene","created":"2021-08-05","cited_by_count":7,"area":null},{"id":"2110.12985","title":"Goal-Aware Cross-Entropy for Multi-Target Reinforcement Learning","created":"2021-10-25","cited_by_count":7,"area":null},{"id":"2210.10913","title":"Palm up: Playing in the Latent Manifold for Unsupervised Pretraining","created":"2022-10-19","cited_by_count":7,"area":null},{"id":"2304.12164","title":"USA-Net: Unified Semantic and Affordance Representations for Robot Memory","created":"2023-04-24","cited_by_count":7,"area":null},{"id":"2503.14229","title":"HA-VLN 2.0: An Open Benchmark and Leaderboard for Human-Aware Navigation in Discrete and Continuous Environments with Dynamic Multi-Human Interactions","created":"2025-03-18","cited_by_count":7,"area":null},{"id":"2108.09823","title":"Embodied AI-Driven Operation of Smart Cities: A Concise Review","created":"2021-08-22","cited_by_count":6,"area":null},{"id":"2305.00348","title":"Modality-invariant Visual Odometry for Embodied Vision","created":"2023-04-29","cited_by_count":6,"area":null},{"id":"2306.09077","title":"Estimating Generic 3D Room Structures from 2D Annotations","created":"2023-06-15","cited_by_count":6,"area":null},{"id":"2408.10388","title":"Narrowing the Gap between Vision and Action in Navigation","created":"2024-08-19","cited_by_count":5,"area":null},{"id":"2111.14267","title":"Explore the Potential Performance of Vision-and-Language Navigation Model: a Snapshot Ensemble Method","created":"2021-11-28","cited_by_count":4,"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":"2511.18559","title":"C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction","created":"2025-11-23","cited_by_count":4,"area":null},{"id":"2102.04353","title":"Unlocking Pixels for Reinforcement Learning via Implicit Attention","created":"2021-02-08","cited_by_count":3,"area":null},{"id":"2108.02448","title":"MFuseNet: Robust Depth Estimation with Learned Multiscopic Fusion","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2304.08186","title":"Human Pose Estimation in Monocular Omnidirectional Top-View Images","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2604.17969","title":"E3VS-Bench: A Benchmark for Viewpoint-Dependent Active Perception in 3D Gaussian Splatting Scenes","created":"2026-04-20","cited_by_count":3,"area":null},{"id":"2108.04097","title":"Deep Learning for Embodied Vision Navigation: A Survey","created":"2021-07-07","cited_by_count":2,"area":null},{"id":"2202.01069","title":"Image-based Navigation in Real-World Environments via Multiple Mid-level Representations: Fusion Models, Benchmark and Efficient Evaluation","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2208.14433","title":"A Portable Multiscopic Camera for Novel View and Time Synthesis in Dynamic Scenes","created":"2022-08-30","cited_by_count":2,"area":null},{"id":"2305.13741","title":"L-SA: Learning Under-Explored Targets in Multi-Target Reinforcement Learning","created":"2023-05-23","cited_by_count":2,"area":null},{"id":"2404.08789","title":"Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes","created":"2024-04-12","cited_by_count":2,"area":null},{"id":"2104.08492","title":"A Self-Supervised Auxiliary Loss for Deep RL in Partially Observable Settings","created":"2021-04-17","cited_by_count":1,"area":null},{"id":"2105.00762","title":"VECA : A Toolkit for Building Virtual Environments to Train and Test Human-like Agents","created":"2021-05-03","cited_by_count":1,"area":null},{"id":"2107.06149","title":"MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2209.08685","title":"Meta-simulation for the Automated Design of Synthetic Overhead Imagery","created":"2022-09-19","cited_by_count":1,"area":null},{"id":"2211.05335","title":"Scalable Modular Synthetic Data Generation for Advancing Aerial Autonomy","created":"2022-11-10","cited_by_count":1,"area":null},{"id":"2303.01268","title":"Analyzing Effects of Fake Training Data on the Performance of Deep Learning Systems","created":"2023-03-02","cited_by_count":1,"area":null},{"id":"2309.03100","title":"FArMARe: a Furniture-Aware Multi-task methodology for Recommending Apartments based on the user interests","created":"2023-09-06","cited_by_count":1,"area":null},{"id":"2404.09469","title":"Virtually Enriched NYU Depth V2 Dataset for Monocular Depth Estimation: Do We Need Artificial Augmentation?","created":"2024-04-15","cited_by_count":1,"area":null},{"id":"2411.13251","title":"BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2512.01315","title":"FOD-S2R: A FOD Dataset for Sim2Real Transfer Learning based Object Detection","created":"2025-12-01","cited_by_count":1,"area":null},{"id":"2607.09792","title":"A Comprehensive Survey and Systematic Real-World Evaluation of Embodied Vision-and-Language Navigation","created":"2026-07-09","cited_by_count":1,"area":null},{"id":"2110.05665","title":"Are you doing what I say? On modalities alignment in ALFRED","created":"2021-10-12","cited_by_count":0,"area":null},{"id":"2110.08571","title":"Explore before Moving: A Feasible Path Estimation and Memory Recalling Framework for Embodied Navigation","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2205.15452","title":"MVMO: A Multi-Object Dataset for Wide Baseline Multi-View Semantic Segmentation","created":"2022-05-30","cited_by_count":0,"area":null},{"id":"2206.10312","title":"SAMPLE-HD: Simultaneous Action and Motion Planning Learning Environment","created":"2022-06-01","cited_by_count":0,"area":null},{"id":"2211.11956","title":"A Short Survey of Systematic Generalization","created":"2022-11-22","cited_by_count":0,"area":null},{"id":"2304.02738","title":"Core Challenges in Embodied Vision-Language Planning","created":"2023-04-05","cited_by_count":0,"area":null},{"id":"2307.08016","title":"Breaking Down the Task: A Unit-Grained Hybrid Training Framework for Vision and Language Decision Making","created":"2023-07-16","cited_by_count":0,"area":null},{"id":"2510.23414","title":"Symmetria: A Synthetic Dataset for Learning in Point Clouds","created":"2025-10-27","cited_by_count":0,"area":null}],"next_cursor":null}