{"list":"other","total":58,"rows":[{"id":"2307.15818","title":"RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control","created":"2023-07-28","cited_by_count":3080},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"id":"2504.16054","title":"$\\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization","created":"2025-04-22","cited_by_count":1761},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"2004.02857","title":"Beyond the Nav-Graph: Vision-and-Language Navigation in Continuous Environments","created":"2020-04-06","cited_by_count":441},{"id":"1711.11543","title":"Embodied Question Answering","created":"2017-11-30","cited_by_count":336},{"id":"2011.13922","title":"A Recurrent Vision-and-Language BERT for Navigation","created":"2020-11-26","cited_by_count":302},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2006.13171","title":"ObjectNav Revisited: On Evaluation of Embodied Agents Navigating to Objects","created":"2020-06-23","cited_by_count":244},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2412.04453","title":"NaVILA: Legged Robot Vision-Language-Action Model for Navigation","created":"2024-12-05","cited_by_count":211},{"id":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2406.04882","title":"InstructNav: Zero-shot System for Generic Instruction Navigation in Unexplored Environment","created":"2024-06-07","cited_by_count":157},{"id":"2507.05240","title":"StreamVLN: Streaming Vision-and-Language Navigation via SlowFast Context Modeling","created":"2025-07-07","cited_by_count":118},{"id":"2203.12667","title":"Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directions","created":"2022-03-22","cited_by_count":117},{"id":"2406.09905","title":"Nymeria: A Massive Collection of Multimodal Egocentric Daily Motion in the Wild","created":"2024-06-14","cited_by_count":114},{"id":"1603.02729","title":"Revisiting Active Perception","created":"2016-03-08","cited_by_count":94},{"id":"2404.06609","title":"GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigation","created":"2024-04-09","cited_by_count":94},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2311.06430","title":"GOAT: GO to Any Thing","created":"2023-11-10","cited_by_count":89},{"id":"2509.22548","title":"JanusVLN: Decoupling Semantics and Spatiality with Dual Implicit Memory for Vision-Language Navigation","created":"2025-09-26","cited_by_count":89},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84},{"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},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74},{"id":"2409.14296","title":"HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigation","created":"2024-09-22","cited_by_count":71},{"id":"2207.00254","title":"A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers","created":"2022-07-01","cited_by_count":66},{"id":"2512.08186","title":"Ground Slow, Move Fast: A Dual-System Foundation Model for Generalizable Vision-and-Language Navigation","created":"2025-12-09","cited_by_count":62},{"id":"2503.10630","title":"UniGoal: Towards Universal Zero-shot Goal-oriented Navigation","created":"2025-03-13","cited_by_count":57},{"id":"2112.01001","title":"SEAL: Self-supervised Embodied Active Learning using Exploration and 3D Consistency","created":"2021-12-02","cited_by_count":48},{"id":"2212.00338","title":"3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification","created":"2022-12-01","cited_by_count":46},{"id":"2503.07135","title":"VidBot: Learning Generalizable 3D Actions from In-the-Wild 2D Human Videos for Zero-Shot Robotic Manipulation","created":"2025-03-10","cited_by_count":46},{"id":"1909.09548","title":"An Efficient Sampling-based Method for Online Informative Path Planning in Unknown Environments","created":"2019-09-20","cited_by_count":40},{"id":"2411.05755","title":"End-to-End Navigation with Vision Language Models: Transforming Spatial Reasoning into Question-Answering","created":"2024-11-08","cited_by_count":37},{"id":"2506.15666","title":"Vision in Action: Learning Active Perception from Human Demonstrations","created":"2025-06-18","cited_by_count":37},{"id":"2503.11117","title":"Beyond the Destination: A Novel Benchmark for Exploration-Aware Embodied Question Answering","created":"2025-03-14","cited_by_count":30},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25},{"id":"2602.11598","title":"ABot-N0: Technical Report on the VLA Foundation Model for Versatile Embodied Navigation","created":"2026-02-12","cited_by_count":25},{"id":"2412.08591","title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","created":"2024-12-11","cited_by_count":23},{"id":"2601.08325","title":"ActiveVLA: Injecting Active Perception into Vision-Language-Action Models for Precise 3D Robotic Manipulation","created":"2026-01-13","cited_by_count":18},{"id":"2501.04597","title":"FrontierNet: Learning Visual Cues to Explore","created":"2025-01-08","cited_by_count":12},{"id":"2304.05506","title":"Frontier Semantic Exploration for Visual Target Navigation","created":"2023-04-11","cited_by_count":9},{"id":"2604.08534","title":"ActiveGlasses: Learning Manipulation with Active Vision from Ego-centric Human Demonstration","created":"2026-04-09","cited_by_count":8},{"id":"2512.13250","title":"Toward Ambulatory Vision: Learning Visually-Grounded Active View Selection","created":"2025-12-15","cited_by_count":6},{"id":"2212.11654","title":"Active SLAM: A Review On Last Decade","created":"2022-12-22","cited_by_count":5},{"id":"2506.16623","title":"History-Augmented Vision-Language Models for Frontier-Based Zero-Shot Object Navigation","created":"2025-06-19","cited_by_count":4},{"id":"2603.05377","title":"OpenFrontier: General Navigation with Visual-Language Grounded Frontiers","created":"2026-03-05","cited_by_count":3},{"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},{"id":"2209.10775","title":"MUI-TARE: Multi-Agent Cooperative Exploration with Unknown Initial Position","created":"2022-09-22","cited_by_count":2},{"id":"2508.20981","title":"ActLoc: Learning to Localize on the Move via Active Viewpoint Selection","created":"2025-08-28","cited_by_count":2},{"id":"2511.18140","title":"Observer-Actor: Active Vision Imitation Learning with Sparse-View Gaussian Splatting","created":"2025-11-22","cited_by_count":2},{"id":"2603.00600","title":"I-Perceive: A Foundation Model for Vision-Language Active Perception","created":"2026-02-28","cited_by_count":1},{"id":"2605.17593","title":"Motion-Uncertainty-Aware Next-Best-View Planning for Moving Object Reconstruction","created":"2026-05-17","cited_by_count":1}],"next_cursor":null}