{"total":31,"rows":[{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237,"area":null},{"id":"2504.12782","title":"Set You Straight: Auto-Steering Denoising Trajectories to Sidestep Unwanted Concepts","created":"2025-04-17","cited_by_count":62,"area":null},{"id":"2304.14670","title":"Prompt Engineering for Healthcare: Methodologies and Applications","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2503.23512","title":"SCORE: Story Coherence and Retrieval Enhancement for AI Narratives","created":"2025-03-30","cited_by_count":42,"area":null},{"id":"2505.19369","title":"SETransformer: A Hybrid Attention-Based Architecture for Robust Human Activity Recognition","created":"2025-05-25","cited_by_count":19,"area":null},{"id":"2408.04958","title":"Surgical-VQLA++: Adversarial Contrastive Learning for Calibrated Robust Visual Question-Localized Answering in Robotic Surgery","created":"2024-08-09","cited_by_count":17,"area":null},{"id":"2312.04794","title":"Visual Grounding of Whole Radiology Reports for 3D CT Images","created":"2023-12-08","cited_by_count":13,"area":null},{"id":"2506.23121","title":"CRISP-SAM2: SAM2 with Cross-Modal Interaction and Semantic Prompting for Multi-Organ Segmentation","created":"2025-06-29","cited_by_count":12,"area":null},{"id":"2506.17966","title":"LLM-Enhanced Multimodal Fusion for Cross-Domain Sequential Recommendation","created":"2025-06-22","cited_by_count":11,"area":null},{"id":"2210.05423","title":"Learning to Locate Visual Answer in Video Corpus Using Question","created":"2022-10-11","cited_by_count":10,"area":null},{"id":"2409.05352","title":"PriorDrive: Enhancing Online HD Mapping with Unified Vector Priors","created":"2024-09-09","cited_by_count":10,"area":null},{"id":"2210.14823","title":"Visual Answer Localization with Cross-modal Mutual Knowledge Transfer","created":"2022-10-26","cited_by_count":7,"area":null},{"id":"2501.10348","title":"Credit Risk Identification in Supply Chains Using Generative Adversarial Networks","created":"2025-01-17","cited_by_count":5,"area":null},{"id":"2506.01319","title":"Learning Sparsity for Effective and Efficient Music Performance Question Answering","created":"2025-06-02","cited_by_count":4,"area":null},{"id":"2506.07236","title":"A Narrative Review on Large AI Models in Lung Cancer Screening, Diagnosis, and Treatment Planning","created":"2025-06-08","cited_by_count":4,"area":null},{"id":"2502.05928","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2504.15085","title":"Cognitive-Inspired Hierarchical Attention Fusion With Visual and Textual for Cross-Domain Sequential Recommendation","created":"2025-04-21","cited_by_count":2,"area":null},{"id":"2504.15918","title":"Ask2Loc: Learning to Locate Instructional Visual Answers by Asking Questions","created":"2025-04-22","cited_by_count":2,"area":null},{"id":"2309.12224","title":"Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2502.18185","title":"VesselSAM: Leveraging SAM for Aortic Vessel Segmentation with AtrousLoRA","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2503.17669","title":"TDRI: Two-Phase Dialogue Refinement and Co-Adaptation for Interactive Image Generation","created":"2025-03-22","cited_by_count":1,"area":null},{"id":"2504.03135","title":"Hierarchical Modeling for Medical Visual Question Answering with Cross-Attention Fusion","created":"2025-04-04","cited_by_count":1,"area":null},{"id":"2504.05184","title":"MSA-UNet3+: Multi-Scale Attention UNet3+ with New Supervised Prototypical Contrastive Loss for Coronary DSA Image Segmentation","created":"2025-04-07","cited_by_count":1,"area":null},{"id":"2506.06316","title":"A Reinforcement-Learning-Enhanced LLM Framework for Automated A/B Testing in Personalized Marketing","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2509.17446","title":"MVCL-DAF++: Enhancing Multimodal Intent Recognition via Prototype-Aware Contrastive Alignment and Coarse-to-Fine Dynamic Attention Fusion","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2510.09553","title":"Hierarchical Indexing with Knowledge Enrichment for Multilingual Video Corpus Retrieval","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.06897","title":"Adaptive Morph-Patch Transformer for Aortic Vessel Segmentation","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2607.06618","title":"Overview of the NLPCC 2026 Shared Task 1: Difficulty-Aware Multilingual and Multimodal Medical Instructional Video Understanding Evaluation","created":"2026-07-07","cited_by_count":1,"area":null},{"id":"2509.18562","title":"CPCLDETECTOR: Knowledge Enhancement and Alignment Selection for Chinese Patronizing and Condescending Language Detection","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2510.09224","title":"Tag-Enriched Multi-Attention with Large Language Models for Cross-Domain Sequential Recommendation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2608.06869","title":"DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding","created":"2026-08-07","cited_by_count":0,"area":null}],"next_cursor":null}