{"total":425,"rows":[{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2509.20328","title":"Video models are zero-shot learners and reasoners","created":"2025-09-24","cited_by_count":220,"area":"lr"},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2506.09042","title":"Cosmos-Drive-Dreams: Scalable Synthetic Driving Data Generation with World Foundation Models","created":"2025-06-10","cited_by_count":84,"area":"driving"},{"id":"2508.10333","title":"ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver","created":"2025-08-14","cited_by_count":81,"area":"vla"},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78,"area":"wm"},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78,"area":"mllm"},{"id":"2510.12798","title":"Detect Anything via Next Point Prediction","created":"2025-10-14","cited_by_count":73,"area":null},{"id":"2503.11043","title":"InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences","created":"2025-03-14","cited_by_count":68,"area":"diffusion"},{"id":"2412.03859","title":"CreatiLayout: Siamese Multimodal Diffusion Transformer for Creative Layout-to-Image Generation","created":"2024-12-05","cited_by_count":60,"area":"diffusion"},{"id":"2502.04299","title":"MotionCanvas: Cinematic Shot Design with Controllable Image-to-Video Generation","created":"2025-02-06","cited_by_count":50,"area":"diffusion"},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36,"area":null},{"id":"2501.01097","title":"EliGen: Entity-Level Controlled Image Generation with Regional Attention","created":"2025-01-02","cited_by_count":33,"area":"diffusion"},{"id":"2506.03610","title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","created":"2025-06-04","cited_by_count":31,"area":"agents"},{"id":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","cited_by_count":29,"area":"diffusion"},{"id":"2603.25746","title":"ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling","created":"2026-03-26","cited_by_count":28,"area":null},{"id":"2510.08480","title":"Video-STAR: Reinforcing Open-Vocabulary Action Recognition with Tools","created":"2025-10-09","cited_by_count":26,"area":"mllm"},{"id":"2603.25716","title":"Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models","created":"2026-03-26","cited_by_count":26,"area":"wm"},{"id":"2503.07909","title":"FunGraph: Functionality Aware 3D Scene Graphs for Language-Prompted Scene Interaction","created":"2025-03-10","cited_by_count":23,"area":null},{"id":"2509.25134","title":"LayerD: Decomposing Raster Graphic Designs into Layers","created":"2025-09-29","cited_by_count":21,"area":null},{"id":"2505.20612","title":"Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models","created":"2025-05-27","cited_by_count":20,"area":"mllm"},{"id":"2506.01801","title":"OmniV2V: Versatile Video Generation and Editing via Dynamic Content Manipulation","created":"2025-06-02","cited_by_count":19,"area":"diffusion"},{"id":"2506.05163","title":"FRED: The Florence RGB-Event Drone Dataset","created":"2025-06-05","cited_by_count":16,"area":null},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2501.01855","title":"UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagery","created":"2025-01-03","cited_by_count":15,"area":null},{"id":"2501.13400","title":"YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review","created":"2025-01-23","cited_by_count":15,"area":null},{"id":"2505.13948","title":"Memory-Centric Embodied Question Answering","created":"2025-05-20","cited_by_count":12,"area":null},{"id":"2603.14473","title":"AI Can Learn Scientific Taste","created":"2026-03-15","cited_by_count":11,"area":null},{"id":"2607.18367","title":"AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report","created":"2026-07-20","cited_by_count":11,"area":"wm"},{"id":"2509.04744","title":"WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning","created":"2025-09-05","cited_by_count":10,"area":"lr"},{"id":"2509.10345","title":"Towards Understanding Visual Grounding in Visual Language Models","created":"2025-09-12","cited_by_count":10,"area":"mllm"},{"id":"2512.22519","title":"Clutter-Robust Vision-Language-Action Models through Object-Centric and Geometry Grounding","created":"2025-12-27","cited_by_count":10,"area":"mllm"},{"id":"2508.04564","title":"Drone Detection with Event Cameras","created":"2025-08-06","cited_by_count":9,"area":null},{"id":"2503.23359","title":"VideoFusion: A Spatio-Temporal Collaborative Network for Multi-modal Video Fusion","created":"2025-03-30","cited_by_count":8,"area":null},{"id":"2506.06301","title":"Large Language Models and Their Applications in Roadway Safety and Mobility Enhancement: A Comprehensive Review","created":"2025-05-19","cited_by_count":8,"area":null},{"id":"2509.15237","title":"MICA: Multi-Agent Industrial Coordination Assistant","created":"2025-09-17","cited_by_count":8,"area":null},{"id":"2602.21704","title":"Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language Models","created":"2026-02-25","cited_by_count":8,"area":"mllm"},{"id":"2508.13401","title":"AIM 2025 Rip Current Segmentation (RipSeg) Challenge Report","created":"2025-08-18","cited_by_count":7,"area":null},{"id":"2510.17722","title":"MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues","created":"2025-10-20","cited_by_count":7,"area":"mllm"},{"id":"2601.14706","title":"LookBench: A Live and Holistic Open Benchmark for Fashion Image Retrieval","created":"2026-01-21","cited_by_count":7,"area":null},{"id":"2502.05540","title":"Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector","created":"2025-02-08","cited_by_count":6,"area":null},{"id":"2503.00729","title":"CLEA: Closed-Loop Embodied Agent for Enhancing Task Execution in Dynamic Environments","created":"2025-03-02","cited_by_count":6,"area":"agents"},{"id":"2504.10979","title":"Deep Learning in Concealed Dense Prediction","created":"2025-04-15","cited_by_count":6,"area":null},{"id":"2506.17119","title":"RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and Tracking","created":"2025-06-20","cited_by_count":6,"area":null},{"id":"2507.11001","title":"Learning to Tune Like an Expert: Interpretable and Scene-Aware Navigation via MLLM Reasoning and CVAE-Based Adaptation","created":"2025-07-15","cited_by_count":6,"area":"lr"},{"id":"2508.10704","title":"Beyond conventional vision: RGB-event fusion for robust object detection in dynamic traffic scenarios","created":"2025-08-14","cited_by_count":6,"area":null},{"id":"2509.20745","title":"Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection","created":"2025-09-25","cited_by_count":6,"area":null},{"id":"2509.22460","title":"GeoSketch: A Neural-Symbolic Approach to Geometric Multimodal Reasoning with Auxiliary Line Construction and Affine Transformation","created":"2025-09-26","cited_by_count":6,"area":"lr"},{"id":"2512.20479","title":"UTDesign: A Unified Framework for Stylized Text Editing and Generation in Graphic Design Images","created":"2025-12-23","cited_by_count":6,"area":null},{"id":"2602.14276","title":"ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision","created":"2026-02-15","cited_by_count":6,"area":null},{"id":"2604.08896","title":"GeoMMBench and GeoMMAgent: Toward Expert-Level Multimodal Intelligence in Geoscience and Remote Sensing","created":"2026-04-10","cited_by_count":6,"area":"mllm"},{"id":"2606.17800","title":"MaineCoon: Pursuing A Real-Time Audio-Visual Social World Model","created":"2026-06-16","cited_by_count":6,"area":"wm"},{"id":"2411.14137","title":"VAGUE: Visual Contexts Clarify Ambiguous Expressions","created":"2024-11-21","cited_by_count":5,"area":null},{"id":"2502.11304","title":"Leveraging Multimodal-LLMs Assisted by Instance Segmentation for Intelligent Traffic Monitoring","created":"2025-02-16","cited_by_count":5,"area":null},{"id":"2503.17700","title":"MAMAT: 3D Mamba-Based Atmospheric Turbulence Removal and its Object Detection Capability","created":"2025-03-22","cited_by_count":5,"area":"ssm"},{"id":"2504.02534","title":"Delineate Anything: Resolution-Agnostic Field Boundary Delineation on Satellite Imagery","created":"2025-04-03","cited_by_count":5,"area":null},{"id":"2504.10165","title":"WildLive: Near Real-time Visual Wildlife Tracking onboard UAVs","created":"2025-04-14","cited_by_count":5,"area":null},{"id":"2505.14381","title":"SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation","created":"2025-05-20","cited_by_count":5,"area":"mllm"},{"id":"2507.14505","title":"DCHM: Depth-Consistent Human Modeling for Multiview Detection","created":"2025-07-19","cited_by_count":5,"area":null},{"id":"2511.16937","title":"OmniGround: A Comprehensive Spatio-Temporal Grounding Benchmark for Real-World Complex Scenarios","created":"2025-11-21","cited_by_count":5,"area":null},{"id":"2512.07132","title":"DART: Leveraging Multi-Agent Disagreement for Tool Recruitment in Multimodal Reasoning","created":"2025-12-08","cited_by_count":5,"area":"lr"},{"id":"2602.04315","title":"GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning","created":"2026-02-04","cited_by_count":5,"area":"vla"},{"id":"2604.05271","title":"Toward Unified Fine-Grained Vehicle Classification and Automatic License Plate Recognition","created":"2026-04-07","cited_by_count":5,"area":null},{"id":"2605.23271","title":"EvalVerse: Pipeline-Aware and Expert-Calibrated Benchmarking for Professional Cinematic Video Generation","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2412.07518","title":"Hallucination Elimination and Semantic Enhancement Framework for Vision-Language Models in Traffic Scenarios","created":"2024-12-10","cited_by_count":4,"area":"mllm"},{"id":"2412.14790","title":"YOLOv11 Optimization for Efficient Resource Utilization","created":"2024-12-19","cited_by_count":4,"area":null},{"id":"2502.13134","title":"RHINO: Learning Real-Time Humanoid-Human-Object Interaction from Human Demonstrations","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2505.17114","title":"RAVEN: Query-Guided Representation Alignment for Question Answering over Audio, Video, Embedded Sensors, and Natural Language","created":"2025-05-21","cited_by_count":4,"area":null},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.16737","title":"Cross-modal Offset-guided Dynamic Alignment and Fusion for Weakly Aligned UAV Object Detection","created":"2025-06-20","cited_by_count":4,"area":null},{"id":"2507.11279","title":"Tomato Multi-Angle Multi-Pose Dataset for Fine-Grained Phenotyping","created":"2025-07-15","cited_by_count":4,"area":null},{"id":"2507.13373","title":"Butter: Frequency Consistency and Hierarchical Fusion for Autonomous Driving Object Detection","created":"2025-07-12","cited_by_count":4,"area":null},{"id":"2507.22481","title":"Towards Blind Bitstream-corrupted Video Recovery via a Visual Foundation Model-driven Framework","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2508.19182","title":"SoccerNet 2025 Challenges Results","created":"2025-08-26","cited_by_count":4,"area":null},{"id":"2509.11772","title":"Seg2Track-SAM2: SAM2-based Multi-object Tracking and Segmentation","created":"2025-09-15","cited_by_count":4,"area":null},{"id":"2510.06858","title":"Explaining raw data complexity to improve satellite onboard processing","created":"2025-10-08","cited_by_count":4,"area":null},{"id":"2510.14876","title":"BADAS: Context Aware Collision Prediction Using Real-World Dashcam Data","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2510.25140","title":"DINO-YOLO: Self-Supervised Pre-training for Data-Efficient Object Detection in Civil Engineering Applications","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2512.14040","title":"ChartAgent: A Chart Understanding Framework with Tool Integrated Reasoning","created":"2025-12-16","cited_by_count":4,"area":"lr"},{"id":"2602.00153","title":"See Without Decoding: Motion-Vector-Based Tracking in Compressed Video","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2605.04569","title":"LIVEditor-14B: Lightning Unified Video Editing via In-Context Sparse Attention","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2607.26529","title":"CineWeaver: Training-Free Reference-Controllable Multi-Shot Long Video Generation for Cinematic Storytelling","created":"2026-07-29","cited_by_count":4,"area":"diffusion"},{"id":"2504.11470","title":"SO-DETR: Leveraging Dual-Domain Features and Knowledge Distillation for Small Object Detection","created":"2025-04-11","cited_by_count":3,"area":"distill"},{"id":"2504.13469","title":"HMPE:HeatMap Embedding for Efficient Transformer-Based Small Object Detection","created":"2025-04-18","cited_by_count":3,"area":null},{"id":"2505.04917","title":"A Simple Detector with Frame Dynamics is a Strong Tracker","created":"2025-05-08","cited_by_count":3,"area":null},{"id":"2506.04676","title":"Gen-n-Val: Agentic Image Data Generation and Validation","created":"2025-06-05","cited_by_count":3,"area":"agents"},{"id":"2506.14696","title":"YOLOv11-RGBT: Towards a Comprehensive Single-Stage Multispectral Object Detection Framework","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2507.08729","title":"RoundaboutHD: High-Resolution Real-World Urban Environment Benchmark for Multi-Camera Vehicle Tracking","created":"2025-07-11","cited_by_count":3,"area":null},{"id":"2508.00438","title":"Diffusion-Based User-Guided Data Augmentation for Coronary Stenosis Detection","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2508.16512","title":"Seeing Clearly, Forgetting Deeply: Revisiting Fine-Tuned Video Generators for Driving Simulation","created":"2025-08-22","cited_by_count":3,"area":"wm"},{"id":"2509.21259","title":"Semantic Edge-Cloud Communication for Real-Time Urban Traffic Surveillance with ViT and LLMs over Mobile Networks","created":"2025-09-25","cited_by_count":3,"area":"mllm"},{"id":"2510.20820","title":"CanvasComposer: Personalized Group Photo Generation via a Multi-Reference Canvas","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2510.25497","title":"Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI","created":"2025-10-29","cited_by_count":3,"area":"lr"},{"id":"2510.26114","title":"OracleAgent: A Multimodal Reasoning Agent for Oracle Bone Script Research","created":"2025-10-30","cited_by_count":3,"area":"lr"},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2604.12807","title":"Rethinking Satellite Image Restoration for Onboard AI: A Lightweight Learning-Based Approach","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2604.15065","title":"Learning Where to Embed: Noise-Aware Positional Embedding for Query Retrieval in Small-Object Detection","created":"2026-04-16","cited_by_count":3,"area":null},{"id":"2606.07953","title":"Unification of Closed-Open Industrial Detection Scenarios: New Large-Scale Benchmarks,Challenges and Baselines","created":"2026-06-06","cited_by_count":3,"area":"mllm"},{"id":"2411.10252","title":"Visual-Linguistic Agent: Towards Collaborative Contextual Object Reasoning","created":"2024-11-15","cited_by_count":2,"area":"lr"},{"id":"2411.18871","title":"Comprehensive Performance Evaluation of YOLOv11, YOLOv10, YOLOv9, YOLOv8 and YOLOv5 on Object Detection of Power Equipment","created":"2024-11-28","cited_by_count":2,"area":null}],"next_cursor":"100"}