{"list":"other","total":58,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"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":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"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":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2310.08864","title":"Open X-Embodiment: Robotic Learning Datasets and RT-X Models","created":"2023-10-13","cited_by_count":862},{"id":"1808.00177","title":"Learning Dexterous In-Hand Manipulation","created":"2018-08-01","cited_by_count":687},{"id":"2309.00770","title":"Bias and Fairness in Large Language Models: A Survey","created":"2023-09-02","cited_by_count":639},{"id":"1705.05065","title":"AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehicles","created":"2017-05-15","cited_by_count":523},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2009.13303","title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","created":"2020-09-24","cited_by_count":413},{"id":"2402.10329","title":"Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots","created":"2024-02-15","cited_by_count":394},{"id":"2506.21539","title":"WorldVLA: Towards Autoregressive Action World Model","created":"2025-06-26","cited_by_count":367},{"id":"2410.11758","title":"Latent Action Pretraining from Videos","created":"2024-10-15","cited_by_count":321},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2501.13918","title":"Improving Video Generation with Human Feedback","created":"2025-01-23","cited_by_count":284},{"id":"2102.01293","title":"Scaling Laws for Transfer","created":"2021-02-02","cited_by_count":272},{"id":"2412.03572","title":"Navigation World Models","created":"2024-12-04","cited_by_count":272},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2410.21845","title":"Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning","created":"2024-10-29","cited_by_count":189},{"id":"2107.06829","title":"FAST-LIO2: Fast Direct LiDAR-inertial Odometry","created":"2021-07-14","cited_by_count":183},{"id":"2307.00595","title":"RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shot","created":"2023-07-02","cited_by_count":183},{"id":"2505.12705","title":"DreamGen: Unlocking Generalization in Robot Learning through Video World Models","created":"2025-05-19","cited_by_count":179},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160},{"id":"2410.18647","title":"Data Scaling Laws in Imitation Learning for Robotic Manipulation","created":"2024-10-24","cited_by_count":145},{"id":"2512.15692","title":"mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs","created":"2025-12-17","cited_by_count":142},{"id":"2308.06735","title":"AerialVLN: Vision-and-Language Navigation for UAVs","created":"2023-08-13","cited_by_count":121},{"id":"2601.18692","title":"A Pragmatic VLA Foundation Model","created":"2026-01-26","cited_by_count":103},{"id":"2402.17139","title":"Video as the New Language for Real-World Decision Making","created":"2024-02-27","cited_by_count":87},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2512.06963","title":"VideoVLA: Video Generators Can Be Generalizable Robot Manipulators","created":"2025-12-07","cited_by_count":64},{"id":"2008.08835","title":"EGO-Planner: An ESDF-free Gradient-based Local Planner for Quadrotors","created":"2020-08-20","cited_by_count":55},{"id":"2505.23189","title":"TrackVLA: Embodied Visual Tracking in the Wild","created":"2025-05-29","cited_by_count":47},{"id":"2404.00210","title":"VLM-Social-Nav: Socially Aware Robot Navigation through Scoring using Vision-Language Models","created":"2024-03-30","cited_by_count":46},{"id":"2408.14035","title":"FAST-LIVO2: Fast, Direct LiDAR-Inertial-Visual Odometry","created":"2024-08-26","cited_by_count":44},{"id":"2510.19430","title":"GigaBrain-0: A World Model-Powered Vision-Language-Action Model","created":"2025-10-22","cited_by_count":44},{"id":"2406.14240","title":"CityNav: A Large-Scale Dataset for Real-World Aerial Navigation","created":"2024-06-20","cited_by_count":42},{"id":"2505.15725","title":"UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning","created":"2025-05-21","cited_by_count":31},{"id":"2511.15200","title":"VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation","created":"2025-11-19","cited_by_count":25},{"id":"2512.15258","title":"VLA-AN: An Efficient and Onboard Vision-Language-Action Framework for Aerial Navigation in Complex Environments","created":"2025-12-17","cited_by_count":23},{"id":"2505.12835","title":"FlightGPT: Towards Generalizable and Interpretable UAV Vision-and-Language Navigation with Vision-Language Models","created":"2025-05-19","cited_by_count":22},{"id":"2509.22653","title":"See, Point, Fly: A Learning-Free VLM Framework for Universal Unmanned Aerial Navigation","created":"2025-09-26","cited_by_count":18},{"id":"2512.21714","title":"AstraNav-World: World Model for Foresight Control and Consistency","created":"2025-12-25","cited_by_count":17},{"id":"2409.00895","title":"Whole-Body Control Through Narrow Gaps From Pixels To Action","created":"2024-09-02","cited_by_count":14},{"id":"2512.21887","title":"Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space","created":"2025-12-26","cited_by_count":12},{"id":"2602.05827","title":"Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation","created":"2026-02-05","cited_by_count":10},{"id":"2505.24396","title":"Reactive Aerobatic Flight via Reinforcement Learning","created":"2025-05-30","cited_by_count":5},{"id":"2512.17349","title":"Flying in Clutter on Monocular RGB by Learning in 3D Radiance Fields with Domain Adaptation","created":"2025-12-19","cited_by_count":5},{"id":"2109.07111","title":"Elastic Tracker: A Spatio-temporal Trajectory Planner Flexible Aerial Tracking","created":"2021-09-15","cited_by_count":4}],"next_cursor":null}