{"total":19,"rows":[{"id":"2412.20206","title":"Toward Visual Grounding: A Survey","created":"2024-12-28","cited_by_count":52,"area":null},{"id":"2505.21457","title":"ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning","created":"2025-05-27","cited_by_count":43,"area":null},{"id":"2409.07394","title":"AdaCAD: Adaptively Decoding to Balance Conflicts between Contextual and Parametric Knowledge","created":"2024-09-11","cited_by_count":37,"area":null},{"id":"2408.15205","title":"Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation","created":"2024-08-27","cited_by_count":20,"area":null},{"id":"2506.19848","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2411.01610","title":"Explaining and Improving Contrastive Decoding by Extrapolating the Probabilities of a Huge and Hypothetical LM","created":"2024-11-03","cited_by_count":11,"area":null},{"id":"2505.20764","title":"ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval","created":"2025-05-27","cited_by_count":7,"area":null},{"id":"2412.11927","title":"Transparent and Coherent Procedural Mistake Detection","created":"2024-12-16","cited_by_count":4,"area":null},{"id":"2604.10410","title":"CWCD: Category-Wise Contrastive Decoding for Structured Medical Report Generation","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2504.05305","title":"URECA: Unique Region Caption Anything","created":"2025-04-07","cited_by_count":2,"area":null},{"id":"2601.13707","title":"Attention-space Contrastive Guidance for Efficient Hallucination Mitigation in LVLMs","created":"2026-01-20","cited_by_count":1,"area":null},{"id":"2601.22455","title":"ScribbleSense: Generative Scribble-Based Texture Editing with Intent Prediction","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.03760","title":"RAWDet-7: A Multi-Scenario Benchmark for Object Detection and Description on Quantized RAW Images","created":"2026-02-03","cited_by_count":1,"area":null},{"id":"2603.02896","title":"3D-DRES: Detailed 3D Referring Expression Segmentation","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2509.09958","title":"Zero-Shot Referring Expression Comprehension via Vison-Language True/False Verification","created":"2025-09-12","cited_by_count":0,"area":null},{"id":"2509.16674","title":"FitPro: A Zero-Shot Framework for Interactive Text-based Pedestrian Retrieval in Open World","created":"2025-09-20","cited_by_count":0,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null},{"id":"2604.09368","title":"Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2608.09053","title":"Diagnosing as Cardiologists Do: ECG Agents with Doctor-Grounded Priors for Clinical Reasoning Across Diseases and Populations","created":"2026-08-10","cited_by_count":0,"area":null}],"next_cursor":null}