{"total":171,"rows":[{"id":"2302.00487","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application","created":"2023-01-31","cited_by_count":872,"area":null},{"id":"2210.03094","title":"VIMA: General Robot Manipulation with Multimodal Prompts","created":"2022-10-06","cited_by_count":407,"area":null},{"id":"2308.04352","title":"3D-VisTA: Pre-trained Transformer for 3D Vision and Text Alignment","created":"2023-08-08","cited_by_count":204,"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":"2212.00922","title":"Navigating to Objects in the Real World","created":"2022-12-02","cited_by_count":106,"area":null},{"id":"2407.07035","title":"Vision-and-Language Navigation Today and Tomorrow: A Survey in the Era of Foundation Models","created":"2024-07-09","cited_by_count":79,"area":null},{"id":"2303.16894","title":"ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance","created":"2023-03-29","cited_by_count":70,"area":null},{"id":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70,"area":null},{"id":"2304.04321","title":"ARNOLD: A Benchmark for Language-Grounded Task Learning With Continuous States in Realistic 3D Scenes","created":"2023-04-09","cited_by_count":69,"area":null},{"id":"2310.09605","title":"Penetrative AI: Making LLMs Comprehend the Physical World","created":"2023-10-14","cited_by_count":64,"area":null},{"id":"2303.00304","title":"Renderable Neural Radiance Map for Visual Navigation","created":"2023-03-01","cited_by_count":51,"area":null},{"id":"2303.07820","title":"Adaptive Rotated Convolution for Rotated Object Detection","created":"2023-03-14","cited_by_count":51,"area":null},{"id":"2507.04047","title":"Move to Understand a 3D Scene: Bridging Visual Grounding and Exploration for Efficient and Versatile Embodied Navigation","created":"2025-07-05","cited_by_count":51,"area":null},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47,"area":null},{"id":"2411.12469","title":"AI Flow at the Network Edge","created":"2024-11-19","cited_by_count":46,"area":null},{"id":"2505.05108","title":"Multi-agent Embodied AI: Advances and Future Directions","created":"2025-05-08","cited_by_count":36,"area":null},{"id":"2408.11537","title":"A Survey of Embodied Learning for Object-Centric Robotic Manipulation","created":"2024-08-21","cited_by_count":35,"area":null},{"id":"2508.08086","title":"Matrix-3D: Omnidirectional Explorable 3D World Generation","created":"2025-08-11","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":"2304.09349","title":"LLM as A Robotic Brain: Unifying Egocentric Memory and Control","created":"2023-04-19","cited_by_count":33,"area":null},{"id":"2304.09179","title":"Pretrained Language Models as Visual Planners for Human Assistance","created":"2023-04-17","cited_by_count":28,"area":null},{"id":"2301.03213","title":"EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset","created":"2023-01-09","cited_by_count":27,"area":null},{"id":"2306.13818","title":"AR2-D2:Training a Robot Without a Robot","created":"2023-06-23","cited_by_count":27,"area":null},{"id":"2404.12777","title":"EfficientGS: Streamlining Gaussian Splatting for Large-Scale High-Resolution Scene Representation","created":"2024-04-19","cited_by_count":27,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2410.00255","title":"Robin3D: Improving 3D Large Language Model via Robust Instruction Tuning","created":"2024-09-30","cited_by_count":26,"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":"2507.05763","title":"DreamArt: Generating Interactable Articulated Objects from a Single Image","created":"2025-07-08","cited_by_count":25,"area":null},{"id":"2305.17102","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2202.06481","title":"A Survey on Machine Learning Approaches for Modelling Intuitive Physics","created":"2022-02-14","cited_by_count":20,"area":null},{"id":"2208.00553","title":"Search for or Navigate to? Dual Adaptive Thinking for Object Navigation","created":"2022-08-01","cited_by_count":20,"area":null},{"id":"2311.04193","title":"Selective Visual Representations Improve Convergence and Generalization for Embodied AI","created":"2023-11-07","cited_by_count":19,"area":null},{"id":"2512.19021","title":"VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation","created":"2025-12-22","cited_by_count":19,"area":null},{"id":"2206.08737","title":"N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments","created":"2022-06-17","cited_by_count":16,"area":null},{"id":"2402.04580","title":"A Comprehensive Survey of Cross-Domain Policy Transfer for Embodied Agents","created":"2024-02-07","cited_by_count":16,"area":null},{"id":"2505.01458","title":"A Survey of Robotic Navigation and Manipulation with Physics Simulators in the Era of Embodied AI","created":"2025-05-01","cited_by_count":16,"area":null},{"id":"2601.20354","title":"Everything in Its Place: Benchmarking Spatial Intelligence of Text-to-Image Models","created":"2026-01-28","cited_by_count":16,"area":null},{"id":"2303.13826","title":"Hard Sample Matters a Lot in Zero-Shot Quantization","created":"2023-03-24","cited_by_count":15,"area":null},{"id":"2302.11683","title":"MVTrans: Multi-View Perception of Transparent Objects","created":"2023-02-22","cited_by_count":14,"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":"2407.15447","title":"SIGMA: Sinkhorn-Guided Masked Video Modeling","created":"2024-07-22","cited_by_count":14,"area":null},{"id":"2506.09378","title":"UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2511.20886","title":"V$^{2}$-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence","created":"2025-11-25","cited_by_count":14,"area":null},{"id":"2301.00452","title":"Human-in-the-loop Embodied Intelligence with Interactive Simulation Environment for Surgical Robot Learning","created":"2023-01-01","cited_by_count":13,"area":null},{"id":"2409.01630","title":"SafeEmbodAI: a Safety Framework for Mobile Robots in Embodied AI Systems","created":"2024-09-03","cited_by_count":13,"area":null},{"id":"2502.15336","title":"Exploring Embodied Multimodal Large Models: Development, Datasets, and Future Directions","created":"2025-02-21","cited_by_count":13,"area":null},{"id":"2505.18078","title":"DanceTogether! Identity-Preserving Multi-Person Interactive Video Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2104.12379","title":"Towards Visual Semantics","created":"2021-04-26","cited_by_count":12,"area":null},{"id":"2108.06107","title":"Aspect Sentiment Triplet Extraction Using Reinforcement Learning","created":"2021-08-13","cited_by_count":12,"area":null},{"id":"2304.07007","title":"Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategy","created":"2023-04-14","cited_by_count":12,"area":null},{"id":"2512.04451","title":"StreamEQA: Towards Streaming Video Understanding for Embodied Scenarios","created":"2025-12-04","cited_by_count":12,"area":null},{"id":"2409.19650","title":"Grounding 3D Scene Affordance From Egocentric Interactions","created":"2024-09-29","cited_by_count":11,"area":null},{"id":"2502.08946","title":"The Stochastic Parrot on LLM's Shoulder: A Summative Assessment of Physical Concept Understanding","created":"2025-02-13","cited_by_count":11,"area":null},{"id":"2505.11934","title":"iSegMan: Interactive Segment-and-Manipulate 3D Gaussians","created":"2025-05-17","cited_by_count":11,"area":null},{"id":"2506.03887","title":"Pre$^3$: Enabling Deterministic Pushdown Automata for Faster Structured LLM Generation","created":"2025-06-04","cited_by_count":11,"area":null},{"id":"2405.17424","title":"LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence","created":"2024-05-27","cited_by_count":10,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2108.06180","title":"SPACE: A Simulator for Physical Interactions and Causal Learning in 3D Environments","created":"2021-08-13","cited_by_count":9,"area":null},{"id":"2303.11594","title":"A Review on Machine Theory of Mind","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2306.11377","title":"HabiCrowd: A High Performance Simulator for Crowd-Aware Visual Navigation","created":"2023-06-20","cited_by_count":9,"area":null},{"id":"2408.04034","title":"Task-oriented Sequential Grounding and Navigation in 3D Scenes","created":"2024-08-07","cited_by_count":9,"area":null},{"id":"2506.23127","title":"Unleashing Embodied Task Planning Ability in LLMs via Reinforcement Learning","created":"2025-06-29","cited_by_count":9,"area":null},{"id":"2603.16952","title":"Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies","created":"2026-03-16","cited_by_count":9,"area":null},{"id":"2109.04683","title":"PIP: Physical Interaction Prediction via Mental Simulation with Span Selection","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2111.08826","title":"A Benchmark for Modeling Violation-of-Expectation in Physical Reasoning Across Event Categories","created":"2021-11-16","cited_by_count":8,"area":null},{"id":"2203.17219","title":"SimVQA: Exploring Simulated Environments for Visual Question Answering","created":"2022-03-31","cited_by_count":8,"area":null},{"id":"2206.10665","title":"BOSS: A Benchmark for Human Belief Prediction in Object-context Scenarios","created":"2022-06-21","cited_by_count":8,"area":null},{"id":"2312.10728","title":"Benchmarks for Physical Reasoning AI","created":"2023-12-17","cited_by_count":8,"area":null},{"id":"2401.15132","title":"On the Emergence of Symmetrical Reality","created":"2024-01-26","cited_by_count":8,"area":null},{"id":"2407.03967","title":"Investigating the Role of Instruction Variety and Task Difficulty in Robotic Manipulation Tasks","created":"2024-07-04","cited_by_count":8,"area":null},{"id":"2507.18678","title":"Towards Scalable Spatial Intelligence via 2D-to-3D Data Lifting","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2512.03666","title":"ToG-Bench: Task-Oriented Spatio-Temporal Grounding in Egocentric Videos","created":"2025-12-03","cited_by_count":8,"area":null},{"id":"2209.06428","title":"Semantic Visual Simultaneous Localization and Mapping: A Survey","created":"2022-09-14","cited_by_count":7,"area":null},{"id":"2210.02709","title":"Embodied Referring Expression for Manipulation Question Answering in Interactive Environment","created":"2022-10-06","cited_by_count":7,"area":null},{"id":"2402.03824","title":"A call for embodied AI","created":"2024-02-06","cited_by_count":7,"area":null},{"id":"2410.08530","title":"Ego3DT: Tracking Every 3D Object in Ego-centric Videos","created":"2024-10-11","cited_by_count":7,"area":null},{"id":"2604.17473","title":"Dual-Anchoring: Addressing State Drift in Vision-Language Navigation","created":"2026-04-19","cited_by_count":7,"area":null},{"id":"2305.00348","title":"Modality-invariant Visual Odometry for Embodied Vision","created":"2023-04-29","cited_by_count":6,"area":null},{"id":"2402.15259","title":"Open Ad Hoc Teamwork with Cooperative Game Theory","created":"2024-02-23","cited_by_count":6,"area":null},{"id":"2502.10177","title":"STMA: A Spatio-Temporal Memory Agent for Long-Horizon Embodied Task Planning","created":"2025-02-14","cited_by_count":6,"area":null},{"id":"2505.11191","title":"Multi-Modal Multi-Task (M3T) Federated Foundation Models for Embodied AI: Potentials and Challenges for Edge Integration","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2307.16206","title":"Synthesizing Event-centric Knowledge Graphs of Daily Activities Using Virtual Space","created":"2023-07-30","cited_by_count":5,"area":null},{"id":"2402.00290","title":"MEIA: Multimodal Embodied Perception and Interaction in Unknown Environments","created":"2024-02-01","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":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2507.10894","title":"NavComposer: Composing Language Instructions for Navigation Trajectories through Action-Scene-Object Modularization","created":"2025-07-15","cited_by_count":5,"area":null},{"id":"2110.05836","title":"AVoE: A Synthetic 3D Dataset on Understanding Violation of Expectation for Artificial Cognition","created":"2021-10-12","cited_by_count":4,"area":null},{"id":"2306.09273","title":"Privacy Risks in Reinforcement Learning for Household Robots","created":"2023-06-15","cited_by_count":4,"area":null},{"id":"2406.16578","title":"QuadrupedGPT: Towards a Versatile Quadruped Agent in Open-ended Worlds","created":"2024-06-24","cited_by_count":4,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","cited_by_count":4,"area":null},{"id":"2506.24009","title":"Bridging Physical and Digital Worlds: Embodied Large AI for Future Wireless Systems","created":"2025-06-30","cited_by_count":4,"area":null},{"id":"2508.00400","title":"Sari Sandbox: A Virtual Retail Store Environment for Embodied AI Agents","created":"2025-08-01","cited_by_count":4,"area":null},{"id":"2509.15061","title":"Ask-to-Clarify: Resolving Instruction Ambiguity through Multi-turn Dialogue","created":"2025-09-18","cited_by_count":4,"area":null},{"id":"2511.04029","title":"Faithful Contouring: Near-Lossless 3D Voxel Representation Free from Iso-surface","created":"2025-11-06","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2512.04770","title":"Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges","created":"2025-12-04","cited_by_count":4,"area":null},{"id":"2601.22853","title":"Inference-Time Dynamic Modality Selection for Incomplete Multimodal Classification","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2603.22120","title":"StreamingClaw Technical Report","created":"2026-03-23","cited_by_count":4,"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":"2208.02680","title":"Impact Makes a Sound and Sound Makes an Impact: Sound Guides Representations and Explorations","created":"2022-08-04","cited_by_count":3,"area":null}],"next_cursor":"100"}