{"total":622,"rows":[{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"area":null},{"id":"2411.17440","title":"Identity-Preserving Text-to-Video Generation by Frequency Decomposition","created":"2024-11-26","cited_by_count":158,"area":null},{"id":"2405.12971","title":"BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at once","created":"2024-05-21","cited_by_count":111,"area":null},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106,"area":null},{"id":"2411.14347","title":"DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding","created":"2024-11-21","cited_by_count":89,"area":null},{"id":"2503.17973","title":"PhysTwin: Physics-Informed Reconstruction and Simulation of Deformable Objects from Videos","created":"2025-03-23","cited_by_count":87,"area":null},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82,"area":null},{"id":"2503.20746","title":"PhysGen3D: Crafting a Miniature Interactive World from a Single Image","created":"2025-03-26","cited_by_count":66,"area":null},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63,"area":null},{"id":"2412.04455","title":"Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection","created":"2024-12-05","cited_by_count":63,"area":null},{"id":"2503.16421","title":"MagicMotion: Controllable Video Generation with Dense-to-Sparse Trajectory Guidance","created":"2025-03-20","cited_by_count":61,"area":null},{"id":"2405.17596","title":"GOI: Find 3D Gaussians of Interest with an Optimizable Open-vocabulary Semantic-space Hyperplane","created":"2024-05-27","cited_by_count":53,"area":null},{"id":"2404.13671","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","created":"2024-04-21","cited_by_count":51,"area":null},{"id":"2506.05302","title":"Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos","created":"2025-06-05","cited_by_count":51,"area":null},{"id":"2406.05774","title":"VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction","created":"2024-06-09","cited_by_count":50,"area":null},{"id":"2503.10076","title":"VMBench: A Benchmark for Perception-Aligned Video Motion Generation","created":"2025-03-13","cited_by_count":49,"area":null},{"id":"2504.14920","title":"DyFo: A Training-Free Dynamic Focus Visual Search for Enhancing LMMs in Fine-Grained Visual Understanding","created":"2025-04-21","cited_by_count":49,"area":null},{"id":"2412.13193","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","created":"2024-12-17","cited_by_count":46,"area":null},{"id":"2403.13042","title":"TAPTR: Tracking Any Point with Transformers as Detection","created":"2024-03-19","cited_by_count":45,"area":null},{"id":"2411.17646","title":"SAMWISE: Infusing Wisdom in SAM2 for Text-Driven Video Segmentation","created":"2024-11-26","cited_by_count":44,"area":null},{"id":"2408.03322","title":"Segment Anything in Medical Images and Videos: Benchmark and Deployment","created":"2024-08-06","cited_by_count":42,"area":null},{"id":"2404.10220","title":"Closed-Loop Open-Vocabulary Mobile Manipulation with GPT-4V","created":"2024-04-16","cited_by_count":40,"area":null},{"id":"2510.08568","title":"NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos","created":"2025-10-09","cited_by_count":40,"area":null},{"id":"2411.09823","title":"Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting","created":"2024-11-14","cited_by_count":38,"area":null},{"id":"2405.05173","title":"A Survey on Occupancy Perception for Autonomous Driving: The Information Fusion Perspective","created":"2024-05-08","cited_by_count":37,"area":null},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37,"area":null},{"id":"2410.16770","title":"The Scene Language: Representing Scenes with Programs, Words, and Embeddings","created":"2024-10-22","cited_by_count":36,"area":null},{"id":"2411.18369","title":"G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulation","created":"2024-11-27","cited_by_count":35,"area":null},{"id":"2503.01210","title":"Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond","created":"2025-03-03","cited_by_count":35,"area":null},{"id":"2510.14648","title":"In-Context Learning with Unpaired Clips for Instruction-based Video Editing","created":"2025-10-16","cited_by_count":35,"area":null},{"id":"2408.10123","title":"Learning Precise Affordances from Egocentric Videos for Robotic Manipulation","created":"2024-08-19","cited_by_count":34,"area":null},{"id":"2412.01197","title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","created":"2024-12-02","cited_by_count":34,"area":null},{"id":"2407.10957","title":"Ref-AVS: Refer and Segment Objects in Audio-Visual Scenes","created":"2024-07-15","cited_by_count":33,"area":null},{"id":"2502.12084","title":"VLM2-Bench: A Closer Look at How Well VLMs Implicitly Link Explicit Matching Visual Cues","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2411.12789","title":"Efficient Physics Simulation for 3D Scenes via MLLM-Guided Gaussian Splatting","created":"2024-11-19","cited_by_count":32,"area":null},{"id":"2408.04326","title":"Multi-Scale and Detail-Enhanced Segment Anything Model for Salient Object Detection","created":"2024-08-08","cited_by_count":30,"area":null},{"id":"2412.01745","title":"Horizon-GS: Unified 3D Gaussian Splatting for Large-Scale Aerial-to-Ground Scenes","created":"2024-12-02","cited_by_count":30,"area":null},{"id":"2501.14607","title":"ReferDINO: Referring Video Object Segmentation with Visual Grounding Foundations","created":"2025-01-24","cited_by_count":30,"area":null},{"id":"2504.15278","title":"DRAWER: Digital Reconstruction and Articulation With Environment Realism","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2412.03342","title":"UniVAD: A Training-free Unified Model for Few-shot Visual Anomaly Detection","created":"2024-12-04","cited_by_count":28,"area":null},{"id":"2412.18153","title":"DepthLab: From Partial to Complete","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2404.05268","title":"MC$^2$: Multi-concept Guidance for Customized Multi-concept Generation","created":"2024-04-08","cited_by_count":26,"area":null},{"id":"2405.13659","title":"EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views","created":"2024-05-22","cited_by_count":26,"area":null},{"id":"2502.01720","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","created":"2025-02-03","cited_by_count":25,"area":null},{"id":"2507.15454","title":"ObjectGS: Object-aware Scene Reconstruction and Scene Understanding via Gaussian Splatting","created":"2025-07-21","cited_by_count":25,"area":null},{"id":"2407.07587","title":"Let Occ Flow: Self-Supervised 3D Occupancy Flow Prediction","created":"2024-07-10","cited_by_count":24,"area":null},{"id":"2409.13401","title":"PointSAM: Pointly-Supervised Segment Anything Model for Remote Sensing Images","created":"2024-09-20","cited_by_count":24,"area":null},{"id":"2501.10928","title":"Generative Physical AI in Vision: A Survey","created":"2025-01-19","cited_by_count":24,"area":null},{"id":"2502.11801","title":"3D Gaussian Inpainting with Depth-Guided Cross-View Consistency","created":"2025-02-17","cited_by_count":24,"area":null},{"id":"2502.17288","title":"GaussianFlowOcc: Sparse and Weakly Supervised Occupancy Estimation using Gaussian Splatting and Temporal Flow","created":"2025-02-24","cited_by_count":24,"area":null},{"id":"2407.10341","title":"Affordance-Guided Reinforcement Learning via Visual Prompting","created":"2024-07-14","cited_by_count":23,"area":null},{"id":"2512.17650","title":"Region-Constraint In-Context Generation for Instructional Video Editing","created":"2025-12-19","cited_by_count":23,"area":null},{"id":"2410.22332","title":"Local Policies Enable Zero-shot Long-horizon Manipulation","created":"2024-10-29","cited_by_count":22,"area":null},{"id":"2412.01583","title":"3DSceneEditor: Controllable 3D Scene Editing with Gaussian Splatting","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2502.02548","title":"Mosaic3D: Foundation Dataset and Model for Open-Vocabulary 3D Segmentation","created":"2025-02-04","cited_by_count":22,"area":null},{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"area":null},{"id":"2508.00265","title":"Multimodal Referring Segmentation: A Survey","created":"2025-08-01","cited_by_count":22,"area":null},{"id":"2408.04567","title":"Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2408.06190","title":"FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework","created":"2024-08-12","cited_by_count":21,"area":null},{"id":"2506.09984","title":"InterActHuman: Multi-Concept Human Animation with Layout-Aligned Audio Conditions","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2508.08252","title":"ReferSplat: Referring Segmentation in 3D Gaussian Splatting","created":"2025-08-11","cited_by_count":20,"area":null},{"id":"2406.16531","title":"GIM: A Million-scale Benchmark for Generative Image Manipulation Detection and Localization","created":"2024-06-24","cited_by_count":19,"area":null},{"id":"2411.13019","title":"Open-World Amodal Appearance Completion","created":"2024-11-20","cited_by_count":19,"area":null},{"id":"2411.18548","title":"PhyCAGE: Physically Plausible Compositional 3D Asset Generation from a Single Image","created":"2024-11-27","cited_by_count":19,"area":null},{"id":"2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","created":"2025-06-10","cited_by_count":19,"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":"2604.21915","title":"Vista4D: Video Reshooting with 4D Point Clouds","created":"2026-04-23","cited_by_count":18,"area":null},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"area":null},{"id":"2507.12137","title":"AD-GS: Object-Aware B-Spline Gaussian Splatting for Self-Supervised Autonomous Driving","created":"2025-07-16","cited_by_count":17,"area":null},{"id":"2512.10957","title":"SceneMaker: Open-set 3D Scene Generation with Decoupled De-occlusion and Pose Estimation Model","created":"2025-12-11","cited_by_count":17,"area":null},{"id":"2405.14869","title":"PuzzleAvatar: Assembling 3D Avatars from Personal Albums","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2411.00626","title":"ZIM: Zero-Shot Image Matting for Anything","created":"2024-11-01","cited_by_count":16,"area":null},{"id":"2503.10406","title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","created":"2025-03-13","cited_by_count":16,"area":null},{"id":"2404.11016","title":"MaeFuse: Transferring Omni Features with Pretrained Masked Autoencoders for Infrared and Visible Image Fusion via Guided Training","created":"2024-04-17","cited_by_count":15,"area":null},{"id":"2503.18363","title":"MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2507.05427","title":"OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts","created":"2025-07-07","cited_by_count":15,"area":null},{"id":"2508.05899","title":"HOLODECK 2.0: Vision-Language-Guided 3D World Generation with Editing","created":"2025-08-07","cited_by_count":15,"area":null},{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15,"area":null},{"id":"2405.12461","title":"WorldAfford: Affordance Grounding based on Natural Language Instructions","created":"2024-05-21","cited_by_count":14,"area":null},{"id":"2406.00625","title":"SAM-LAD: Segment Anything Model Meets Zero-Shot Logic Anomaly Detection","created":"2024-06-02","cited_by_count":14,"area":null},{"id":"2407.01942","title":"Certainly Uncertain: A Benchmark and Metric for Multimodal Epistemic and Aleatoric Awareness","created":"2024-07-02","cited_by_count":14,"area":null},{"id":"2510.05560","title":"HoloScene: Simulation-Ready Interactive 3D Worlds from a Single Video","created":"2025-10-07","cited_by_count":14,"area":null},{"id":"2402.02555","title":"High-Quality Entity Segmentation and Grounding","created":"2024-02-04","cited_by_count":13,"area":null},{"id":"2407.04604","title":"PartCraft: Crafting Creative Objects by Parts","created":"2024-07-05","cited_by_count":13,"area":null},{"id":"2409.05606","title":"CustomContrast: A Multilevel Contrastive Perspective For Subject-Driven Text-to-Image Customization","created":"2024-09-09","cited_by_count":13,"area":null},{"id":"2410.01647","title":"3DGS-DET: Empower 3D Gaussian Splatting with Boundary Guidance and Box-Focused Sampling for Indoor 3D Object Detection","created":"2024-10-02","cited_by_count":13,"area":null},{"id":"2508.03227","title":"Trace3D: Consistent Segmentation Lifting via Gaussian Instance Tracing","created":"2025-08-05","cited_by_count":13,"area":null},{"id":"2508.14893","title":"Virtual Community: An Open World for Humans, Robots, and Society","created":"2025-08-20","cited_by_count":13,"area":null},{"id":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2403.18605","title":"FlexEdit: Flexible and Controllable Diffusion-based Object-centric Image Editing","created":"2024-03-27","cited_by_count":12,"area":null},{"id":"2412.09997","title":"GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark","created":"2024-12-13","cited_by_count":12,"area":null},{"id":"2503.01646","title":"OpenGS-SLAM: Open-Set Dense Semantic SLAM with 3D Gaussian Splatting for Object-Level Scene Understanding","created":"2025-03-03","cited_by_count":12,"area":null},{"id":"2503.11081","title":"MoMa-Kitchen: A 100K+ Benchmark for Affordance-Grounded Last-Mile Navigation in Mobile Manipulation","created":"2025-03-14","cited_by_count":12,"area":null},{"id":"2510.11549","title":"ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?","created":"2025-10-13","cited_by_count":12,"area":null},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12,"area":null},{"id":"2405.06964","title":"ManiFoundation Model for General-Purpose Robotic Manipulation of Contact Synthesis with Arbitrary Objects and Robots","created":"2024-05-11","cited_by_count":11,"area":null},{"id":"2410.18195","title":"Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments","created":"2024-10-23","cited_by_count":11,"area":null}],"next_cursor":"100"}