{"list":"other","total":81,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"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":"2304.13705","title":"Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware","created":"2023-04-23","cited_by_count":1568},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"1812.07035","title":"On the Continuity of Rotation Representations in Neural Networks","created":"2018-12-17","cited_by_count":1214},{"id":"1706.04261","title":"The \"something something\" video database for learning and evaluating visual common sense","created":"2017-06-13","cited_by_count":1103},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"1804.02748","title":"Scaling Egocentric Vision: The EPIC-KITCHENS Dataset","created":"2018-04-08","cited_by_count":795},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2410.07864","title":"RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation","created":"2024-10-10","cited_by_count":691},{"id":"2506.18088","title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","created":"2025-06-22","cited_by_count":518},{"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":"2406.02523","title":"RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robots","created":"2024-06-04","cited_by_count":407},{"id":"2503.06669","title":"AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systems","created":"2025-03-09","cited_by_count":405},{"id":"2407.08693","title":"Robotic Control via Embodied Chain-of-Thought Reasoning","created":"2024-07-11","cited_by_count":346},{"id":"2409.17146","title":"Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models","created":"2024-09-25","cited_by_count":329},{"id":"2510.10274","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","created":"2025-10-11","cited_by_count":303},{"id":"2510.13626","title":"LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models","created":"2025-10-15","cited_by_count":303},{"id":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2406.10721","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","created":"2024-06-15","cited_by_count":251},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"id":"2506.07339","title":"Real-Time Execution of Action Chunking Flow Policies","created":"2025-06-09","cited_by_count":216},{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"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":"2410.24221","title":"EgoMimic: Scaling Imitation Learning via Egocentric Video","created":"2024-10-31","cited_by_count":175},{"id":"2412.13877","title":"RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation","created":"2024-12-18","cited_by_count":175},{"id":"2302.01877","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","created":"2023-02-03","cited_by_count":149},{"id":"2505.23705","title":"Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Better","created":"2025-05-29","cited_by_count":146},{"id":"2506.04308","title":"RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics","created":"2025-06-04","cited_by_count":127},{"id":"2504.13059","title":"RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins","created":"2025-04-17","cited_by_count":121},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2602.11236","title":"ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning","created":"2026-02-11","cited_by_count":103},{"id":"2507.15597","title":"Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos","created":"2025-07-21","cited_by_count":102},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95},{"id":"2602.16710","title":"EgoScale: Scaling Dexterous Manipulation with Diverse Egocentric Human Data","created":"2026-02-18","cited_by_count":94},{"id":"2509.00576","title":"Galaxea Open-World Dataset and G0 Dual-System VLA Model","created":"2025-08-30","cited_by_count":92},{"id":"2310.20550","title":"CapsFusion: Rethinking Image-Text Data at Scale","created":"2023-10-31","cited_by_count":90},{"id":"2508.20072","title":"Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policies","created":"2025-08-27","cited_by_count":90},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79},{"id":"2603.04356","title":"RoboCasa365: A Large-Scale Simulation Framework for Training and Benchmarking Generalist Robots","created":"2026-03-04","cited_by_count":79},{"id":"2503.13441","title":"Humanoid Policy ~ Human Policy","created":"2025-03-17","cited_by_count":78},{"id":"2511.17441","title":"RoboCOIN: An Open-Sourced Bimanual Robotic Data Collection for Integrated Manipulation","created":"2025-11-21","cited_by_count":78},{"id":"2605.00078","title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","created":"2026-04-30","cited_by_count":75},{"id":"2503.00779","title":"Phantom: Training Robots Without Robots Using Only Human Videos","created":"2025-03-02","cited_by_count":70},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70},{"id":"2601.12993","title":"Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalization","created":"2026-01-19","cited_by_count":66},{"id":"2604.07607","title":"EgoVerse: An Egocentric Human Dataset for Robot Learning from Around the World","created":"2026-04-08","cited_by_count":57},{"id":"2505.08243","title":"Training Strategies for Efficient Embodied Reasoning","created":"2025-05-13","cited_by_count":55},{"id":"2602.12215","title":"LDA-1B: Scaling Latent Dynamics Action Model via Universal Embodied Data Ingestion","created":"2026-02-12","cited_by_count":52},{"id":"2511.16651","title":"InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy","created":"2025-11-20","cited_by_count":50},{"id":"2601.02456","title":"InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation","created":"2026-01-05","cited_by_count":50},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50},{"id":"2508.09976","title":"Masquerade: Learning from In-the-wild Human Videos using Data-Editing","created":"2025-08-13","cited_by_count":43},{"id":"2603.22078","title":"Do World Action Models Generalize Better than VLAs? A Robustness Study","created":"2026-03-23","cited_by_count":36},{"id":"2512.24653","title":"RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied Intelligence","created":"2025-12-31","cited_by_count":32},{"id":"2605.03269","title":"RLDX-1 Technical Report","created":"2026-05-05","cited_by_count":28},{"id":"2602.21736","title":"Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the Wild","created":"2026-02-25","cited_by_count":15},{"id":"2412.07215","title":"RoboTron-Mani: All-in-One Multimodal Large Model for Robotic Manipulation","created":"2024-12-10","cited_by_count":14},{"id":"2602.09973","title":"RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation","created":"2026-02-10","cited_by_count":14},{"id":"2407.04292","title":"DaDu-Corki: Algorithm-Architecture Co-Design for Embodied AI-powered Robotic Manipulation","created":"2024-07-05","cited_by_count":13},{"id":"2605.08774","title":"ProcVLM: Learning Procedure-Grounded Progress Rewards for Robotic Manipulation","created":"2026-05-09","cited_by_count":9},{"id":"2605.13119","title":"Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models","created":"2026-05-13","cited_by_count":9},{"id":"2508.13103","title":"Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy","created":"2025-08-18","cited_by_count":8},{"id":"2602.09722","title":"Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization","created":"2026-02-10","cited_by_count":7},{"id":"2509.14630","title":"Toward Embodiment Equivariant Vision-Language-Action Policy","created":"2025-09-18","cited_by_count":5},{"id":"2602.11464","title":"EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos","created":"2026-02-12","cited_by_count":2}],"next_cursor":null}