{"total":247,"rows":[{"id":"2601.11109","title":"Vision-as-Inverse-Graphics Agent via Interleaved Multimodal Reasoning","created":"2026-01-16","cited_by_count":49,"area":"lr"},{"id":"2602.09153","title":"SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes","created":"2026-02-09","cited_by_count":46,"area":"agents"},{"id":"2607.05391","title":"LLM-as-a-Verifier: A General-Purpose Verification Framework","created":"2026-07-06","cited_by_count":30,"area":"lr"},{"id":"2603.05449","title":"RealWonder: Real-Time Physical Action-Conditioned Video Generation","created":"2026-03-05","cited_by_count":22,"area":null},{"id":"2603.11633","title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","created":"2026-03-12","cited_by_count":19,"area":null},{"id":"2604.19092","title":"RoboWM-Bench: A Benchmark for Evaluating World Models in Robotic Manipulation","created":"2026-04-21","cited_by_count":19,"area":"wm"},{"id":"2602.16863","title":"SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation","created":"2026-02-18","cited_by_count":15,"area":null},{"id":"2602.02473","title":"HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videos","created":"2026-02-02","cited_by_count":14,"area":null},{"id":"2605.10922","title":"Pixal3D: Pixel-Aligned 3D Generation from Images","created":"2026-05-11","cited_by_count":14,"area":null},{"id":"2608.27549","title":"Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning","created":"2026-08-27","cited_by_count":14,"area":"lr"},{"id":"2603.03482","title":"Beyond Pixel Histories: World Models with Persistent 3D State","created":"2026-03-03","cited_by_count":13,"area":"wm"},{"id":"2603.27449","title":"LOME: Learning Human-Object Manipulation with Action-Conditioned Egocentric World Model","created":"2026-03-28","cited_by_count":13,"area":"wm"},{"id":"2605.19587","title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2606.02580","title":"Thinking in Blender: Staged Executable Inverse Graphics with Vision-Language Models","created":"2026-06-01","cited_by_count":10,"area":"mllm"},{"id":"2512.05343","title":"SpaceControl: Introducing Test-Time Spatial Control to 3D Generative Modeling","created":"2025-12-05","cited_by_count":9,"area":null},{"id":"2607.19190","title":"Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents","created":"2026-07-21","cited_by_count":8,"area":"wm"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2601.01050","title":"EgoGrasp: World-Space Hand-Object Interaction Estimation from Egocentric Videos","created":"2026-01-03","cited_by_count":7,"area":"diffusion"},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2604.27106","title":"Reconstruction by Generation: 3D Multi-Object Scene Reconstruction from Sparse Observations","created":"2026-04-29","cited_by_count":7,"area":null},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2511.21945","title":"GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2602.09023","title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","created":"2026-02-09","cited_by_count":6,"area":"vla"},{"id":"2602.15733","title":"MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction","created":"2026-02-17","cited_by_count":6,"area":"deeprl"},{"id":"2603.07552","title":"ReconDrive: Fast Feed-Forward 4D Gaussian Splatting for Autonomous Driving Scene Reconstruction","created":"2026-03-08","cited_by_count":6,"area":"driving"},{"id":"2604.11789","title":"LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2605.30338","title":"REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"id":"2607.00033","title":"Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstration","created":"2026-06-22","cited_by_count":6,"area":"deeprl"},{"id":"2607.07459","title":"EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI","created":"2026-07-08","cited_by_count":6,"area":"agents"},{"id":"2607.20889","title":"Engine-Native Editable 3D World Reconstruction with Objects and Lighting","created":"2026-07-23","cited_by_count":6,"area":null},{"id":"2601.05237","title":"ObjectForesight: Predicting Future 3D Object Trajectories from Human Videos","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2603.19231","title":"MonoArt: Progressive Structural Reasoning for Monocular Articulated 3D Reconstruction","created":"2026-03-19","cited_by_count":5,"area":null},{"id":"2603.23386","title":"SIMART: Decomposing Monolithic Meshes into Sim-ready Articulated Assets via MLLM","created":"2026-03-24","cited_by_count":5,"area":null},{"id":"2604.01479","title":"RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space","created":"2026-04-01","cited_by_count":5,"area":null},{"id":"2606.03994","title":"SimuScene: Simulation-Ready Compositional 3D Scene Reconstruction from a Single Image","created":"2026-06-02","cited_by_count":5,"area":null},{"id":"2606.13652","title":"World Tracing: Generative Pixel-Aligned Geometry Beyond the Visible","created":"2026-06-11","cited_by_count":5,"area":"diffusion"},{"id":"2602.02331","title":"TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkour","created":"2026-02-02","cited_by_count":4,"area":null},{"id":"2602.04672","title":"AGILE: Hand-Object Interaction Reconstruction from Video via Agentic Generation","created":"2026-02-04","cited_by_count":4,"area":"agents"},{"id":"2602.08058","title":"Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling","created":"2026-02-08","cited_by_count":4,"area":null},{"id":"2602.20150","title":"Simulation-Ready Cluttered Scene Estimation via Physics-aware Joint Shape and Pose Optimization","created":"2026-02-23","cited_by_count":4,"area":null},{"id":"2603.18782","title":"Points-to-3D: Structure-Aware 3D Generation with Point Cloud Priors","created":"2026-03-19","cited_by_count":4,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2605.20290","title":"PhysOmni: Physics-Grounded Multi-Object Scene Generation from a Single Image with Real-Time Interaction","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2605.23699","title":"CRONOS: Benchmarking Counterfactual Physical Consistency in Video Models","created":"2026-05-22","cited_by_count":4,"area":"wm"},{"id":"2606.13676","title":"Modality Forcing for Scalable Spatial Generation","created":"2026-06-11","cited_by_count":4,"area":null},{"id":"2608.04575","title":"PhysMind: From Video to Executable Worlds for Training-Free Physical Reasoning","created":"2026-08-05","cited_by_count":4,"area":"lr"},{"id":"2512.00960","title":"Efficient and Scalable Monocular Human-Object Interaction Motion Reconstruction","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2512.07394","title":"Reconstructing Objects along Hand Interaction Timelines in Egocentric Video","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2512.11061","title":"VDAWorld: World Modelling via VLM-Directed Abstraction and Simulation","created":"2025-12-11","cited_by_count":3,"area":"wm"},{"id":"2602.01630","title":"Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks","created":"2026-02-02","cited_by_count":3,"area":"wm"},{"id":"2602.02974","title":"SceneLinker: Compositional 3D Scene Generation via Semantic Scene Graph from RGB Sequences","created":"2026-02-03","cited_by_count":3,"area":null},{"id":"2602.05293","title":"Fast-SAM3D: 3Dfy Anything in Images but Faster","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.16085","title":"Interact3D: Compositional 3D Generation of Interactive Objects","created":"2026-03-17","cited_by_count":3,"area":null},{"id":"2604.10789","title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2604.12929","title":"Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2604.16170","title":"neuralCAD-Edit: An Expert Benchmark for Multimodal-Instructed 3D CAD Model Editing","created":"2026-04-17","cited_by_count":3,"area":null},{"id":"2604.17623","title":"ViPS: Video-informed Pose Spaces for Auto-Rigged Meshes","created":"2026-04-19","cited_by_count":3,"area":"diffusion"},{"id":"2605.20373","title":"SUGAR: A Scalable Human-Video-Driven Generalizable Humanoid Loco-Manipulation Learning Framework","created":"2026-05-19","cited_by_count":3,"area":null},{"id":"2606.21596","title":"$\\phi$-Scene: Physically Grounded Image-to-3D Scene Reconstruction","created":"2026-06-19","cited_by_count":3,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.01015","title":"SuperFlex: Deformable Superquadrics for Point Cloud Decomposition","created":"2026-07-01","cited_by_count":3,"area":null},{"id":"2607.20660","title":"Axolotl3D: a Unified Framework for Faithful 3D Shape Completion","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2603.07307","title":"StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models","created":"2026-03-07","cited_by_count":2,"area":"inference"},{"id":"2603.22972","title":"WorldMesh: Generating Navigable Multi-Room 3D Scenes via Mesh-Conditioned Image Diffusion","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.25726","title":"AnyHand: A Large-Scale Synthetic Dataset for RGB(-D) Hand Pose Estimation","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2604.01207","title":"TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.05182","title":"LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2604.10125","title":"PhyMix: Towards Physically Consistent Single-Image 3D Indoor Scene Generation with Implicit--Explicit Optimization","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2605.11756","title":"Focusable Monocular Depth Estimation","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.14398","title":"ChronoAgentic: A Code-based Multi-Agent World Simulator for Physically Grounded Simulation Construction","created":"2026-05-14","cited_by_count":2,"area":"wm"},{"id":"2605.15843","title":"WorldAct: Activating Monolithic 3D Worlds into Interactive-Ready Object-Centric Scenes","created":"2026-05-15","cited_by_count":2,"area":"wm"},{"id":"2606.01458","title":"LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World","created":"2026-05-31","cited_by_count":2,"area":"vla"},{"id":"2606.08057","title":"EgoAERO: Learning Dexterous Manipulation from a Single Egocentric Video without Object Assets","created":"2026-06-06","cited_by_count":2,"area":null},{"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":"2606.29941","title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2606.30598","title":"Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2606.31680","title":"ShellMaker: Language-Guided Exterior Completion under Structural Constraints","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2607.02075","title":"HandsOnWorld: Unconstrained Egocentric Video Generation with Camera-Disentangled Hand Control","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.07601","title":"CARLA-GS: Decoupling Representation, Reasoning, and Physics Simulation for Autonomous Driving Corner-Case Synthesis","created":"2026-07-08","cited_by_count":2,"area":"wm"},{"id":"2607.16355","title":"PhysAgent: Reflective Agentic Physics Control for Physically Plausible Video Generation","created":"2026-07-17","cited_by_count":2,"area":"agents"},{"id":"2607.24298","title":"UMI3D: Robust 3D Generation on Unconstrained Multi-Image Inputs via Simultaneous Focus Cross-Attention Routing","created":"2026-07-27","cited_by_count":2,"area":null},{"id":"2608.30821","title":"Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling","created":"2026-08-31","cited_by_count":2,"area":null},{"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":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2512.07596","title":"More than Segmentation: Benchmarking SAM 3 for Segmentation, 3D Perception, and Reconstruction in Robotic Surgery","created":"2025-12-08","cited_by_count":1,"area":null},{"id":"2512.08188","title":"Embodied Tree of Thoughts: Deliberate Manipulation Planning with Embodied World Model","created":"2025-12-09","cited_by_count":1,"area":"wm"},{"id":"2601.09211","title":"Affostruction: 3D Affordance Grounding with Generative Reconstruction","created":"2026-01-14","cited_by_count":1,"area":null},{"id":"2601.21081","title":"Shape of Thought: Progressive Object Assembly via Visual Chain-of-Thought","created":"2026-01-28","cited_by_count":1,"area":"lr"},{"id":"2602.10278","title":"ERGO: Excess-Risk-Guided Optimization for High-Fidelity Monocular 3D Gaussian Splatting","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2603.05425","title":"RelaxFlow: Text-Driven Amodal 3D Generation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.14152","title":"SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2603.15614","title":"Tri-Prompting: Video Diffusion with Unified Control over Scene, Subject, and Motion","created":"2026-03-16","cited_by_count":1,"area":"diffusion"},{"id":"2603.16868","title":"MessyKitchens: Contact-rich object-level 3D scene reconstruction","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2604.02736","title":"THOM: Generating Physically Plausible Hand-Object Meshes From Text","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.06725","title":"Enhancing MLLM Spatial Understanding via Active 3D Scene Exploration for Multi-Perspective Reasoning","created":"2026-04-08","cited_by_count":1,"area":"lr"},{"id":"2604.20841","title":"DeVI: Physics-based Dexterous Human-Object Interaction via Synthetic Video Imitation","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.00345","title":"Pose-Aware Diffusion for 3D Generation","created":"2026-05-01","cited_by_count":1,"area":null}],"next_cursor":"100"}