{"total":24,"rows":[{"id":"2405.13949","title":"PitVQA: Image-grounded Text Embedding LLM for Visual Question Answering in Pituitary Surgery","created":"2024-05-22","cited_by_count":23,"area":null},{"id":"2503.19740","title":"LEMON: A Large Endoscopic MONocular Dataset and Foundation Model for Perception in Surgical Settings","created":"2025-03-25","cited_by_count":20,"area":null},{"id":"2410.21348","title":"Large Language Model Benchmarks in Medical Tasks","created":"2024-10-28","cited_by_count":17,"area":null},{"id":"2506.17873","title":"SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model","created":"2025-06-22","cited_by_count":13,"area":null},{"id":"2505.24287","title":"EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding","created":"2025-05-30","cited_by_count":11,"area":null},{"id":"2501.07468","title":"From Screens to Scenes: A Survey of Embodied AI in Healthcare","created":"2025-01-13","cited_by_count":10,"area":null},{"id":"2403.16736","title":"Creating a Digital Twin of Spinal Surgery: A Proof of Concept","created":"2024-03-25","cited_by_count":9,"area":null},{"id":"2502.14886","title":"Surgical Scene Understanding in the Era of Foundation AI Models: A Comprehensive Review","created":"2025-02-16","cited_by_count":8,"area":null},{"id":"2511.03325","title":"SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2502.02438","title":"Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2508.06546","title":"Statistical Confidence Rescoring for Robust 3D Scene Graph Generation from Multi-View Images","created":"2025-08-05","cited_by_count":5,"area":null},{"id":"2501.09555","title":"Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2505.12890","title":"Specialized Foundation Models for Intelligent Operating Rooms","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2509.20941","title":"Decoding the Surgical Scene: A Scoping Review of Scene Graphs in Surgery","created":"2025-09-25","cited_by_count":3,"area":null},{"id":"2601.12224","title":"Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion","created":"2026-01-18","cited_by_count":3,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2603.16822","title":"Surg$\\Sigma$: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2606.15647","title":"Towards Next-Generation Healthcare: A Survey of Medical Embodied AI for Perception, Decision-Making, and Action","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2509.06831","title":"Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2603.09696","title":"TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.19920","title":"PanORama: Multiview Consistent Panoptic Segmentation in Operating Rooms","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2605.17915","title":"SurgLQA: Scalable Long-Horizon Surgical Video Question Answering","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2608.15336","title":"SAGE-OR: Semi-supervised Adaptive Scene Graph Generation for Operating Rooms","created":"2026-08-15","cited_by_count":0,"area":null}],"next_cursor":null}