{"list":"other","total":56,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"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":"2406.09246","title":"OpenVLA: An Open-Source Vision-Language-Action Model","created":"2024-06-13","cited_by_count":2887},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"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":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2212.06817","title":"RT-1: Robotics Transformer for Real-World Control at Scale","created":"2022-12-13","cited_by_count":2061},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2503.14734","title":"GR00T N1: An Open Foundation Model for Generalist Humanoid Robots","created":"2025-03-18","cited_by_count":1225},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1612.00603","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","created":"2016-12-02","cited_by_count":979},{"id":"2403.12945","title":"DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset","created":"2024-03-19","cited_by_count":852},{"id":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"1909.12271","title":"RLBench: The Robot Learning Benchmark & Learning Environment","created":"2019-09-26","cited_by_count":689},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2308.12952","title":"BridgeData V2: A Dataset for Robot Learning at Scale","created":"2023-08-24","cited_by_count":657},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2302.00111","title":"Learning Universal Policies via Text-Guided Video Generation","created":"2023-01-31","cited_by_count":522},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2402.17177","title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models","created":"2024-02-27","cited_by_count":477},{"id":"2310.06114","title":"Learning Interactive Real-World Simulators","created":"2023-10-09","cited_by_count":458},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2312.08344","title":"FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects","created":"2023-12-13","cited_by_count":429},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2410.00425","title":"ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AI","created":"2024-10-01","cited_by_count":229},{"id":"2401.00025","title":"Any-point Trajectory Modeling for Policy Learning","created":"2023-12-28","cited_by_count":215},{"id":"2310.10625","title":"Video Language Planning","created":"2023-10-16","cited_by_count":162},{"id":"2409.16283","title":"Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation","created":"2024-09-24","cited_by_count":153},{"id":"2405.01527","title":"Track2Act: Predicting Point Tracks from Internet Videos enables Generalizable Robot Manipulation","created":"2024-05-02","cited_by_count":124},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91},{"id":"2512.15840","title":"Large Video Planner Enables Generalizable Robot Control","created":"2025-12-17","cited_by_count":70},{"id":"2310.18999","title":"DynPoint: Dynamic Neural Point For View Synthesis","created":"2023-10-29","cited_by_count":37},{"id":"2506.01943","title":"Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control","created":"2025-06-02","cited_by_count":34},{"id":"2507.13097","title":"GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training","created":"2025-07-17","cited_by_count":32},{"id":"2410.15461","title":"EVA: An Embodied World Model for Future Video Anticipation","created":"2024-10-20","cited_by_count":28},{"id":"2511.19971","title":"VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction","created":"2025-11-25","cited_by_count":28},{"id":"2412.19584","title":"DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction","created":"2024-12-27","cited_by_count":26},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26},{"id":"2604.18564","title":"MultiWorld: Scalable Multi-Agent Multi-View Video World Models","created":"2026-04-20","cited_by_count":23},{"id":"2512.17661","title":"Vidarc: Embodied Video Diffusion Model for Closed-loop Control","created":"2025-12-19","cited_by_count":15},{"id":"2505.23171","title":"RoboTransfer: Controllable Geometry-Consistent Video Diffusion for Manipulation Policy Transfer","created":"2025-05-29","cited_by_count":7},{"id":"2601.11266","title":"Skill-Aware Diffusion for Generalizable Robotic Manipulation","created":"2026-01-16","cited_by_count":3},{"id":"2511.14019","title":"RISE: Single Static Radar-based Indoor Scene Understanding","created":"2025-11-18","cited_by_count":2}],"next_cursor":null}