{"total":19,"rows":[{"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":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","cited_by_count":13,"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":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","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":"2506.22808","title":"MedEthicsQA: A Comprehensive Question Answering Benchmark for Medical Ethics Evaluation of LLMs","created":"2025-06-28","cited_by_count":8,"area":null},{"id":"2605.08712","title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","created":"2026-05-09","cited_by_count":4,"area":null},{"id":"2505.12890","title":"Specialized Foundation Models for Intelligent Operating Rooms","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2501.15326","title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","created":"2025-01-25","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":"2603.16024","title":"Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.21132","title":"SurgOnAir: Hierarchy-Aware Real-Time Surgical Video Commentary","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2606.27484","title":"Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2603.05732","title":"From Phase Grounding to Intelligent Surgical Narratives","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2607.01751","title":"MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.04761","title":"DeGenseGS: Geometrically and Semantically Decoupled Surgical Scene Understanding in 4D Gaussian Splatting","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.04676","title":"SurgNarrator: A Generative Retrieval Framework for Surgical Video Understanding","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2610.09800","title":"Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video Generation","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}