{"total":47,"rows":[{"id":"2601.21957","title":"PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing","created":"2026-01-29","cited_by_count":57,"area":null},{"id":"2606.03264","title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","created":"2026-06-02","cited_by_count":21,"area":null},{"id":"2512.12309","title":"WeDetect: Fast Open-Vocabulary Object Detection as Retrieval","created":"2025-12-13","cited_by_count":14,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2512.04082","title":"PosterCopilot: Toward Layout Reasoning and Controllable Editing for Professional Graphic Design","created":"2025-12-03","cited_by_count":6,"area":null},{"id":"2511.18333","title":"ConsistCompose: Unified Multimodal Layout Control for Image Composition","created":"2025-11-23","cited_by_count":5,"area":null},{"id":"2605.00663","title":"Affordance Agent Harness: Verification-Gated Skill Orchestration","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2602.03892","title":"Audit After Segmentation: Reference-Free Mask Quality Assessment for Language-Referred Audio-Visual Segmentation","created":"2026-02-03","cited_by_count":2,"area":null},{"id":"2603.07098","title":"NuNext: Reframing Nucleus Detection as Next-Point Detection","created":"2026-03-07","cited_by_count":2,"area":null},{"id":"2603.24690","title":"UniICL: Systematizing Unified Multimodal In-context Learning through a Capability-Oriented Taxonomy","created":"2026-03-25","cited_by_count":2,"area":null},{"id":"2512.05597","title":"Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2603.07985","title":"On the Feasibility and Opportunity of Autoregressive 3D Object Detection","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.15558","title":"Panoramic Affordance Prediction","created":"2026-03-16","cited_by_count":1,"area":null},{"id":"2604.02773","title":"Generalized Small Object Detection:A Point-Prompted Paradigm and Benchmark","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.08921","title":"TAIHRI: Task-Aware 3D Human Keypoints Localization for Close-Range Human-Robot Interaction","created":"2026-04-10","cited_by_count":1,"area":null},{"id":"2605.20147","title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2609.07072","title":"Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive Detection","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2609.35718","title":"Hard Vision, Easy Vision: What GPT-6 Astra Reveals Across Computer Vision","created":"2026-09-28","cited_by_count":1,"area":null},{"id":"2602.01753","title":"ObjEmbed: Towards Universal Multimodal Object Embeddings","created":"2026-02-02","cited_by_count":0,"area":null},{"id":"2602.15962","title":"Automated Re-Identification of Holstein-Friesian Cattle in Dense Crowds","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2603.12751","title":"Show, Don't Tell: Detecting Novel Objects by Watching Human Videos","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.19451","title":"LoFi: Location-Aware Fine-Grained Representation Learning for Chest X-ray","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.01974","title":"Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.27928","title":"Training-Free Tunnel Defect Inspection and Engineering Interpretation via Visual Recalibration and Entity Reconstruction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.04501","title":"Example-Based Object Detection","created":"2026-05-06","cited_by_count":0,"area":null},{"id":"2605.14923","title":"SceneParser: Hierarchical Scene Parsing for Visual Semantics Understanding","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2605.16515","title":"SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2605.29429","title":"One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.08267","title":"UniRef-UAV: A Multimodal Benchmark for Universal Referring in UAV Imagery","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.08541","title":"VocaDet: Sample-Driven Open-Vocabulary Object Detection and Segmentation via Visual Tokenization and Vector Database Retrieval","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.27278","title":"OVEarth-Bench: Evaluating Category Breadth and Query Diversity for Open-Vocabulary Earth Observation","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.00976","title":"Location-Aware Fine-Grained Representation Learning for Medical Vision Foundation Models","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.02791","title":"Better, Stronger, Faster, and Broader: Structured All-Mask Prediction for MLLM-Based Segmentation","created":"2026-08-03","cited_by_count":0,"area":null},{"id":"2608.03322","title":"LocAnyMed: Vision-Language Grounding for Multimodal Medical Images","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.09880","title":"Financial Numerical Prediction and Allocation as Token Generation","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2608.10524","title":"Rethinking Text-Based Image Retrieval in Specific Domain","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.18996","title":"GrabVG: Graph-Attentive Binding for Visual Grounding in UAV Imagery","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.26101","title":"RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video Editing","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.28192","title":"Locate Anything in Videos: Rethinking Efficient Generative Spatio-Temporal Video Grounding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.28567","title":"GeBDA: Building Damage Assessment as Text-Based Sequence Prediction","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29126","title":"Efficient Language-to-Vision Feature Injection for Referring Single-Object Tracking","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.34271","title":"Scaling Versatile 3D Assets Editing with a Million-Scale Dataset","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35955","title":"HEIR: Learning Human-Entity Interactions with Functional Roles","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.13239","title":"Jag: Direct Box Prediction for Efficient Visual Grounding","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.14647","title":"Can Synthetic UAV Benchmarks Be Trusted? Real-Synthetic Validation for UAV Model Selection","created":"2026-10-10","cited_by_count":0,"area":null},{"id":"2610.15769","title":"Hand2Robot: Object-Centric 4D Hand Reconstruction from Human Demonstrations for Robotics","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.19419","title":"WinARDet: Compressed Window Auto-Regression for Long-Horizon Vision-Language Grounding","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}