{"total":28,"rows":[{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"area":null},{"id":"2308.07156","title":"SAM Meets Robotic Surgery: An Empirical Study on Generalization, Robustness and Adaptation","created":"2023-08-14","cited_by_count":30,"area":null},{"id":"2304.14674","title":"SAM Meets Robotic Surgery: An Empirical Study in Robustness Perspective","created":"2023-04-28","cited_by_count":24,"area":null},{"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":"2412.02621","title":"Medical Multimodal Foundation Models in Clinical Diagnosis and Treatment: Applications, Challenges, and Future Directions","created":"2024-12-03","cited_by_count":18,"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":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","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":"2409.04732","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery","created":"2024-09-07","cited_by_count":12,"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":"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":"2405.08272","title":"VS-Assistant: Versatile Surgery Assistant on the Demand of Surgeons","created":"2024-05-14","cited_by_count":7,"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":"2503.18296","title":"Surgical Action Planning with Large Language Models","created":"2025-03-24","cited_by_count":4,"area":null},{"id":"2410.07824","title":"Exploring Foundation Models in Remote Sensing Image Change Detection: A Comprehensive Survey","created":"2024-10-10","cited_by_count":3,"area":null},{"id":"2511.01458","title":"When to Trust the Answer: Question-Aligned Semantic Nearest Neighbor Entropy for Safer Surgical VQA","created":"2025-11-03","cited_by_count":3,"area":null},{"id":"2402.03093","title":"AI-Enhanced Virtual Reality in Medicine: A Comprehensive Survey","created":"2024-02-05","cited_by_count":2,"area":null},{"id":"2502.15184","title":"Hierarchical Context Transformer for Multi-level Semantic Scene Understanding","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2507.00209","title":"SurgiSR4K: A High-Resolution Endoscopic Video Dataset for Robotic-Assisted Minimally Invasive Procedures","created":"2025-06-30","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":"2511.12026","title":"Bridging Vision and Language for Robust Context-Aware Surgical Point Tracking: The VL-SurgPT Dataset and Benchmark","created":"2025-11-15","cited_by_count":0,"area":null},{"id":"2511.15159","title":"Generating Natural-Language Surgical Feedback: From Structured Representation to Domain-Grounded Evaluation","created":"2025-11-19","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":"2605.17915","title":"SurgLQA: Scalable Long-Horizon Surgical Video Question Answering","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.23068","title":"RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering","created":"2026-05-21","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}],"next_cursor":null}