{"total":128,"rows":[{"id":"2508.10898","title":"Puppeteer: Rig and Animate Your 3D Models","created":"2025-08-14","cited_by_count":43,"area":null},{"id":"2508.13998","title":"Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation","created":"2025-08-19","cited_by_count":38,"area":"lr"},{"id":"2607.05391","title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","created":"2026-07-06","cited_by_count":30,"area":"lr"},{"id":"2502.07531","title":"VidCRAFT3: Camera, Object, and Lighting Control for Image-to-Video Generation","created":"2025-02-11","cited_by_count":25,"area":null},{"id":"2512.02015","title":"Generative Video Motion Editing with 3D Point Tracks","created":"2025-12-01","cited_by_count":23,"area":null},{"id":"2511.16661","title":"Dexterity from Smart Lenses: Multi-Fingered Robot Manipulation with In-the-Wild Human Demonstrations","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2511.21690","title":"TraceGen: World Modeling in 3D Trace Space Enables Learning from Cross-Embodiment Videos","created":"2025-11-26","cited_by_count":15,"area":"wm"},{"id":"2507.06224","title":"EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow","created":"2025-07-08","cited_by_count":11,"area":"offlinerl"},{"id":"2606.28128","title":"PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation","created":"2026-06-26","cited_by_count":10,"area":null},{"id":"2606.01399","title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","created":"2026-05-31","cited_by_count":8,"area":null},{"id":"2605.23856","title":"Point Tracking Improves World Action Models","created":"2026-05-22","cited_by_count":7,"area":"wm"},{"id":"2505.01288","title":"ViSA-Flow: Accelerating Robot Skill Learning via Large-Scale Video Semantic Action Flow","created":"2025-05-02","cited_by_count":6,"area":null},{"id":"2605.05126","title":"ConsisVLA-4D: Advancing Spatiotemporal Consistency in Efficient 3D-Perception and 4D-Reasoning for Robotic Manipulation","created":"2026-05-06","cited_by_count":6,"area":"lr"},{"id":"2606.11324","title":"Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models","created":"2026-06-09","cited_by_count":6,"area":"lr"},{"id":"2506.08694","title":"MoSiC: Optimal-Transport Motion Trajectory for Dense Self-Supervised Learning","created":"2025-06-10","cited_by_count":5,"area":null},{"id":"2511.18373","title":"MASS: Motion-Aware Spatial-Temporal Grounding for Physics Reasoning and Comprehension in Vision-Language Models","created":"2025-11-23","cited_by_count":5,"area":"lr"},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2603.25739","title":"MegaFlow: Zero-Shot Large Displacement Optical Flow","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2605.18467","title":"InstructAV2AV: Instruction-Guided Audio-Video Joint Editing","created":"2026-05-18","cited_by_count":5,"area":null},{"id":"2606.18558","title":"MolmoMotion: Forecasting Point Trajectories in 3D with Language Instruction","created":"2026-06-17","cited_by_count":5,"area":null},{"id":"2503.19953","title":"Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals","created":"2025-03-25","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","cited_by_count":4,"area":null},{"id":"2603.25791","title":"ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2608.15555","title":"RigidBench: Evaluating Rigid-Body Physics in Video Generation Models","created":"2026-08-16","cited_by_count":4,"area":null},{"id":"2509.18043","title":"Prepare Before You Act: Learning From Humans to Rearrange Initial States","created":"2025-09-22","cited_by_count":3,"area":"offlinerl"},{"id":"2509.19115","title":"Track-On2: Enhancing Online Point Tracking with Memory","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2512.20606","title":"Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking","created":"2025-12-23","cited_by_count":3,"area":"diffusion"},{"id":"2602.04441","title":"SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking","created":"2026-02-04","cited_by_count":3,"area":"synth"},{"id":"2603.17426","title":"SHIFT: Motion Alignment in Video Diffusion Models with Adversarial Hybrid Fine-Tuning","created":"2026-03-18","cited_by_count":3,"area":"diffusion"},{"id":"2603.22193","title":"PAM: A Pose-Appearance-Motion Engine for Sim-to-Real HOI Video Generation","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2607.06555","title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","created":"2026-07-07","cited_by_count":3,"area":null},{"id":"2610.03715","title":"4DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic Scenes","created":"2026-10-02","cited_by_count":3,"area":null},{"id":"2510.01388","title":"VENTURA: Adapting Image Diffusion Models for Unified Task Conditioned Navigation","created":"2025-10-01","cited_by_count":2,"area":"diffusion"},{"id":"2510.19819","title":"Is This Tracker On? A Benchmark Protocol for Dynamic Tracking","created":"2025-10-22","cited_by_count":2,"area":null},{"id":"2510.26443","title":"PointSt3R: Point Tracking through 3D Grounded Correspondence","created":"2025-10-30","cited_by_count":2,"area":null},{"id":"2512.05044","title":"Geometry-Aware Single-Image 4D Synthesis via Dense Trajectory Generation","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2603.03485","title":"Phys4D: Fine-Grained Physics-Consistent 4D Modeling from Video Diffusion","created":"2026-03-03","cited_by_count":2,"area":"wm"},{"id":"2605.26649","title":"On the Generalization Capabilities, Design Choices and Limitations of Keypoint Imitation Learning","created":"2026-05-26","cited_by_count":2,"area":"offlinerl"},{"id":"2606.23688","title":"Lift4D: Harmonizing Single-View 3D Estimation for 4D Reconstruction In-the-Wild","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2606.26087","title":"MVTrack4Gen: Multi-View Point Tracking as Geometric Supervision for 4D Video Generation","created":"2026-06-24","cited_by_count":2,"area":"diffusion"},{"id":"2607.13451","title":"Learning Physics-Guided Residual Dynamics for Deformable Object Simulation","created":"2026-07-15","cited_by_count":2,"area":null},{"id":"2607.25918","title":"DC-WAM: Dynamic-Centric Visual Supervision and Reasoning for World-Action Models","created":"2026-07-28","cited_by_count":2,"area":"wm"},{"id":"2608.29537","title":"AGM: Achievement-Grounded Memory for Closed-Loop Agents with Frozen VLA Policies","created":"2026-08-30","cited_by_count":2,"area":"vla"},{"id":"2609.04911","title":"TourPhysics: Bringing Physics to World Models for Exploration and Manipulation from a Single Image","created":"2026-09-04","cited_by_count":2,"area":"wm"},{"id":"2609.17521","title":"PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control","created":"2026-09-15","cited_by_count":2,"area":null},{"id":"2504.00161","title":"SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance","created":"2025-03-31","cited_by_count":1,"area":null},{"id":"2602.22376","title":"AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2603.17704","title":"DancingBox: A Lightweight MoCap System for Character Animation from Physical Proxies","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2606.13497","title":"SPARC: Reliable Spatial Annotations from Robot Demonstrations at Scale","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.19889","title":"SurgVista: Long-Horizon Surgical World Modeling with Plausible Instrument-Tissue Dynamics","created":"2026-06-18","cited_by_count":1,"area":"wm"},{"id":"2606.23090","title":"Flow as Flow: Modeling Robot Velocity Fields as Probability Velocity Fields for Flow-Based Object Manipulation","created":"2026-06-22","cited_by_count":1,"area":"diffusion"},{"id":"2606.25344","title":"Follow Your Track: Precise Skeleton Animation Controlled by 3D Trajectories","created":"2026-06-24","cited_by_count":1,"area":null},{"id":"2606.30047","title":"Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2606.30608","title":"UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.03723","title":"OmniTacTune: Policy-Agnostic Real-World RL for Tactile Residual Adaptation of Visual Policies","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2607.20653","title":"PhysCoRe: Physics-Corrected Residual World Models for Material-Aware Deformable Dynamics","created":"2026-07-22","cited_by_count":1,"area":"wm"},{"id":"2607.27749","title":"Articulated Object Reconstruction from Rest-State Observation","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.05215","title":"VLAff: Vision-Language-Affordance Model for Unified Actionable Affordances","created":"2026-08-05","cited_by_count":1,"area":null},{"id":"2608.17283","title":"UniQuery4R: Unified 4D Scene Reconstruction from a Single Query","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.20107","title":"BeyondMasks: Evaluating Causal and Physical Consistency in Video Object Removal","created":"2026-08-20","cited_by_count":1,"area":null},{"id":"2608.29137","title":"Chat-Edit-3D++: Interactive 3D and 4D Scene Editing via Large Language Models","created":"2026-08-29","cited_by_count":1,"area":"mllm"},{"id":"2609.01899","title":"TAPVid-MV: A Benchmark for Tracking Any Point in 3D Across Multiple Views","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.03199","title":"RoboTok: A Scalable Data Engine for Internet Demonstration Video Retrieval and Dexterous Manipulation Learning","created":"2026-09-02","cited_by_count":1,"area":null},{"id":"2609.09145","title":"Point4D: Long-range 4D Motion Reconstruction","created":"2026-09-08","cited_by_count":1,"area":null},{"id":"2609.30404","title":"POIL: Point-based One-Shot Imitation Learning with Stable Dynamical Systems","created":"2026-09-24","cited_by_count":1,"area":"offlinerl"},{"id":"2411.14833","title":"Cell as Point: One-Stage Framework for Efficient Cell Tracking","created":"2024-11-22","cited_by_count":0,"area":null},{"id":"2511.12026","title":"Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2512.10607","title":"Track and Caption Any Motion: Open-Vocabulary Spatiotemporal Captioning via Trajectory-Conditioned Generation","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.10628","title":"K-Track: Kalman-Enhanced Tracking for Accelerating Deep Point Trackers on Edge Devices","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.10956","title":"Stereo4DWalker: Learning 4D-aware Embodied Urban Navigation from Internet Stereo Videos","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2512.17504","title":"InsertAnywhere: Geometrically Grounded and Optics-Aware Video Object Insertion","created":"2025-12-19","cited_by_count":0,"area":"diffusion"},{"id":"2603.06471","title":"Match4Annotate: Cross-Video Annotation Transfer in Ultrasound via Implicit Feature Flow-Guided Matching","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.17068","title":"TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2603.21618","title":"4DGS360: 360{\\deg} Gaussian Reconstruction of Dynamic Objects from a Single Video","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.27012","title":"UMI-Underwater: Learning Underwater Manipulation without Underwater Teleoperation","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.22160","title":"GenMatter: Perceiving Physical Objects with Generative Matter Models","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.04527","title":"Velox: Learning Representations of 4D Geometry and Appearance","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.12140","title":"EchoTracker2: Enhancing Myocardial Point Tracking by Modeling Local Motion","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15497","title":"AnyAct: Towards Human Reenactment of Character Motion From Video","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.17303","title":"LongDPM: Overlap-Aware 4D Reconstruction from Long Monocular Videos","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2605.18743","title":"WorldString: Actionable World Representation","created":"2026-05-18","cited_by_count":0,"area":"wm"},{"id":"2606.10645","title":"ManiSplat: Manipulation Trajectory Synthesis from Monocular Video via Decoupled 3D Gaussian Splatting","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.10988","title":"AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.28593","title":"Animation2Code: Evaluating Temporal Visual Reasoning in Video-to-Code Generation","created":"2026-06-26","cited_by_count":0,"area":"lr"},{"id":"2607.00579","title":"EPO: Boosting 3D Foundation Models with Edge-based Pose Optimization","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.05390","title":"Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models","created":"2026-07-06","cited_by_count":0,"area":"wm"},{"id":"2607.08408","title":"Track2Map: Online Deformable SLAM with Motion-Aware Pose Optimization in Robotic Surgery","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.11644","title":"Motion4Motion: Motion Transfer Across Subjects at Inference","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.12939","title":"Point Tracking in Surgery--The 2025 Surgical Tattoos in Infrared Challenge (STIRC2025)","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2607.14968","title":"Stitch-Inferencer: Enhance Endoscopic Video Segmentation and Tracking via Panoramic Reconstruction","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.15268","title":"Motion-Conditioned Multi-View Fusion for Myocardial Infarction Localization from Echocardiography","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.15699","title":"GoStop: Reinforcement Learning for Adaptive Temporal Aggregation in Event-Based Feature Tracking","created":"2026-07-17","cited_by_count":0,"area":"deeprl"},{"id":"2607.18153","title":"Robust Multimodal Dynamic Object Segmentation","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2607.25984","title":"Schr\\\"odinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.02006","title":"ASTRA: Asynchronous Spatio-Temporal Reconstruction via Trajectory Alignment","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.04995","title":"Promptable Animal Pose Tracking Across Species","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05799","title":"XEWorld: Can Action-Conditioned World Models Generalize to Unseen Robot Embodiments?","created":"2026-08-06","cited_by_count":0,"area":"wm"},{"id":"2608.08016","title":"EgoTrack3D: A Modular Framework for Egocentric 3D Object Tracking","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2608.11425","title":"VLMs Win a Systematic Evaluation of Underwater Image Reconstruction","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.17935","title":"Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment","created":"2026-08-18","cited_by_count":0,"area":null}],"next_cursor":"100"}