{"list":"other","total":74,"rows":[{"id":"1707.06347","title":"Proximal Policy Optimization Algorithms","created":"2017-07-20","cited_by_count":15215},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2410.24164","title":"$\\pi_0$: A Vision-Language-Action Flow Model for General Robot Control","created":"2024-10-31","cited_by_count":2407},{"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":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2405.12213","title":"Octo: An Open-Source Generalist Robot Policy","created":"2024-05-20","cited_by_count":1484},{"id":"2306.03310","title":"LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning","created":"2023-06-05","cited_by_count":1410},{"id":"2511.16719","title":"SAM 3: Segment Anything with Concepts","created":"2025-11-20","cited_by_count":906},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2502.19645","title":"Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success","created":"2025-02-27","cited_by_count":883},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"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":"2501.09747","title":"FAST: Efficient Action Tokenization for Vision-Language-Action Models","created":"2025-01-16","cited_by_count":665},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"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":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"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":"2312.13139","title":"Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation","created":"2023-12-20","cited_by_count":364},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2203.01577","title":"HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction","created":"2022-03-03","cited_by_count":327},{"id":"2601.21998","title":"Causal World Modeling for Robot Control","created":"2026-01-29","cited_by_count":321},{"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":"2601.16163","title":"Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning","created":"2026-01-22","cited_by_count":300},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"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":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165},{"id":"2603.17240","title":"GigaWorld-Policy: An Efficient Action-Centered World--Action Model","created":"2026-03-18","cited_by_count":139},{"id":"2604.15483","title":"${\\pi}_{0.7}$: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities","created":"2026-04-16","cited_by_count":138},{"id":"2510.12276","title":"Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Model","created":"2025-10-14","cited_by_count":134},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129},{"id":"2604.05014","title":"StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing","created":"2026-04-06","cited_by_count":112},{"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":"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":"2604.26694","title":"Unified 4D World Action Modeling from Video Priors with Asynchronous Denoising","created":"2026-04-29","cited_by_count":71},{"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":"2604.27792","title":"Motubrain: An Advanced World Action Model for Robot Control","created":"2026-04-30","cited_by_count":57},{"id":"2606.15768","title":"LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policies","created":"2026-06-14","cited_by_count":52},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50},{"id":"2606.09811","title":"AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routing","created":"2026-06-08","cited_by_count":46},{"id":"2607.04434","title":"RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies","created":"2026-07-05","cited_by_count":40},{"id":"2606.19531","title":"ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?","created":"2026-06-17","cited_by_count":38},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34},{"id":"2511.09484","title":"SPIDER: Scalable Physics-Informed Dexterous Retargeting","created":"2025-11-12","cited_by_count":32},{"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":"2602.09849","title":"BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generation","created":"2026-02-10","cited_by_count":30},{"id":"2607.15330","title":"Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories","created":"2026-07-16","cited_by_count":29},{"id":"2607.06403","title":"From Foundation to Application: Improving VLA Models in Practice","created":"2026-07-07","cited_by_count":26},{"id":"2604.20100","title":"JoyAI-RA 0.1: A Foundation Model for Robotic Autonomy","created":"2026-04-22","cited_by_count":23},{"id":"2606.14409","title":"Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack","created":"2026-06-12","cited_by_count":22},{"id":"2609.07398","title":"OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining","created":"2026-09-07","cited_by_count":22},{"id":"2507.06219","title":"Is Diversity All You Need for Scalable Robotic Manipulation?","created":"2025-07-08","cited_by_count":20},{"id":"2604.23570","title":"EgoLive: A Large-Scale Egocentric Dataset from Real-World Human Tasks","created":"2026-04-26","cited_by_count":20},{"id":"2608.11739","title":"G0.5: One Autoregressive Stream for Robot Reasoning and Action","created":"2026-08-12","cited_by_count":18},{"id":"2602.04877","title":"CoWTracker: Tracking by Warping instead of Correlation","created":"2026-02-04","cited_by_count":14},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12},{"id":"2606.06155","title":"AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding","created":"2026-06-04","cited_by_count":12},{"id":"2608.02580","title":"Ego2Robot: Scalable Robot Data Synthesis from Egocentric Human Data","created":"2026-08-03","cited_by_count":11},{"id":"2606.12604","title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","created":"2026-06-10","cited_by_count":8},{"id":"2605.15735","title":"UAM: A Dual-Stream Perspective on Forgetting in VLA Training","created":"2026-05-15","cited_by_count":5},{"id":"2608.12122","title":"HandEdit: A Unified Benchmark for Egocentric Human-to-Robot Dexterous Hand Image Editing","created":"2026-08-12","cited_by_count":5},{"id":"2606.08828","title":"Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video","created":"2026-06-07","cited_by_count":3}],"next_cursor":null}