{"total":68,"rows":[{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42,"area":null},{"id":"2312.07353","title":"CLIP in Medical Imaging: A Survey","created":"2023-12-12","cited_by_count":40,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37,"area":"mllm"},{"id":"2406.07471","title":"OphNet: A Large-Scale Video Benchmark for Ophthalmic Surgical Workflow Understanding","created":"2024-06-11","cited_by_count":32,"area":null},{"id":"2506.02555","title":"SurgVLM: A Large Vision-Language Model and Systematic Evaluation Benchmark for Surgical Intelligence","created":"2025-06-03","cited_by_count":31,"area":"mllm"},{"id":"2411.15421","title":"OphCLIP: Hierarchical Retrieval-Augmented Learning for Ophthalmic Surgical Video-Language Pretraining","created":"2024-11-23","cited_by_count":29,"area":"mllm"},{"id":"2503.02579","title":"MM-OR: A Large Multimodal Operating Room Dataset for Semantic Understanding of High-Intensity Surgical Environments","created":"2025-03-04","cited_by_count":28,"area":null},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25,"area":null},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2407.19305","title":"GP-VLS: A general-purpose vision language model for surgery","created":"2024-07-27","cited_by_count":17,"area":"mllm"},{"id":"2504.21051","title":"Multimodal Large Language Models for Medicine: A Comprehensive Survey","created":"2025-04-29","cited_by_count":16,"area":"mllm"},{"id":"2509.10555","title":"SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning","created":"2025-09-09","cited_by_count":16,"area":"mllm"},{"id":"2401.00678","title":"General-purpose foundation models for increased autonomy in robot-assisted surgery","created":"2024-01-01","cited_by_count":15,"area":null},{"id":"2503.10265","title":"SurgRAW: Multi-Agent Workflow with Chain of Thought Reasoning for Robotic Surgical Video Analysis","created":"2025-03-13","cited_by_count":15,"area":"lr"},{"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":"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":"2506.23309","title":"SurgTPGS: Semantic 3D Surgical Scene Understanding with Text Promptable Gaussian Splatting","created":"2025-06-29","cited_by_count":7,"area":"mllm"},{"id":"2603.06570","title":"SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning","created":"2026-03-06","cited_by_count":7,"area":"lr"},{"id":"2505.10764","title":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","created":"2025-05-16","cited_by_count":6,"area":"mllm"},{"id":"2504.02799","title":"Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence","created":"2025-04-03","cited_by_count":5,"area":"mllm"},{"id":"2506.19694","title":"UltraAD: Fine-Grained Ultrasound Anomaly Classification via Few-Shot CLIP Adaptation","created":"2025-06-24","cited_by_count":5,"area":null},{"id":"2403.13756","title":"Enhancing Gait Video Analysis in Neurodegenerative Diseases by Knowledge Augmentation in Vision Language Model","created":"2024-03-20","cited_by_count":4,"area":"mllm"},{"id":"2503.11392","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","created":"2025-03-14","cited_by_count":4,"area":null},{"id":"2506.20254","title":"Recognizing Surgical Phases Anywhere: Few-Shot Test-time Adaptation and Task-graph Guided Refinement","created":"2025-06-25","cited_by_count":4,"area":null},{"id":"2602.05638","title":"SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos","created":"2026-02-05","cited_by_count":4,"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":"2504.16612","title":"Federated EndoViT: Pretraining Vision Transformers via Federated Learning on Endoscopic Image Collections","created":"2025-04-23","cited_by_count":3,"area":null},{"id":"2505.01766","title":"Multimodal Graph Representation Learning for Robust Surgical Workflow Recognition with Adversarial Feature Disentanglement","created":"2025-05-03","cited_by_count":3,"area":null},{"id":"2509.15596","title":"EyePCR: A Comprehensive Benchmark for Fine-Grained Perception, Knowledge Comprehension and Clinical Reasoning in Ophthalmic Surgery","created":"2025-09-19","cited_by_count":3,"area":"lr"},{"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":"2603.12787","title":"Generalized Recognition of Basic Surgical Actions Enables Skill Assessment and Vision-Language-Model-based Surgical Planning","created":"2026-03-13","cited_by_count":3,"area":null},{"id":"2603.24539","title":"CliPPER: Contextual Video-Language Pretraining on Long-form Intraoperative Surgical Procedures for Event Recognition","created":"2026-03-25","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":"2503.19670","title":"fine-CLIP: Enhancing Zero-Shot Fine-Grained Surgical Action Recognition with Vision-Language Models","created":"2025-03-25","cited_by_count":2,"area":"mllm"},{"id":"2507.05007","title":"Multi-modal Representations for Fine-grained Multi-label Critical View of Safety Recognition","created":"2025-07-07","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":"2606.25905","title":"SurgAtlas: A Large-Scale Surgical Video-Language Dataset with 2,391 Hours of Open and Minimally Invasive Surgery","created":"2026-06-24","cited_by_count":2,"area":null},{"id":"2603.06999","title":"TrajPred: Trajectory-Conditioned Joint Embedding Prediction for Surgical Instrument-Tissue Interaction Recognition in Vision-Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2603.29966","title":"Scaling Video Pretraining for Surgical Foundation Models","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.00784","title":"An Approach to Enriching Surgical Video Datasets for Fine-Grained Spatial-Temporal Understanding of Vision-Language Models","created":"2026-04-01","cited_by_count":1,"area":"mllm"},{"id":"2604.18134","title":"Can LLM-Generated Text Empower Surgical Vision-Language Pre-training?","created":"2026-04-20","cited_by_count":1,"area":"mllm"},{"id":"2606.31245","title":"HyperVLP: Enhancing Hierarchical Surgical Video-Language Pre-training in Hyperbolic Space","created":"2026-06-30","cited_by_count":1,"area":"mllm"},{"id":"2607.23694","title":"Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentation","created":"2026-07-26","cited_by_count":1,"area":null},{"id":"2608.22879","title":"Large-Small Model Collaboration for Zero-Shot Surgical Phase Recognition","created":"2026-08-24","cited_by_count":1,"area":null},{"id":"2503.23130","title":"Can DeepSeek Reason Like a Surgeon? An Empirical Evaluation for Vision-Language Understanding in Robotic-Assisted Surgery","created":"2025-03-29","cited_by_count":0,"area":"lr"},{"id":"2509.06831","title":"Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis","created":"2025-09-08","cited_by_count":0,"area":null},{"id":"2509.19885","title":"Towards Self-Supervised Foundation Models for Critical Care Time Series","created":"2025-09-24","cited_by_count":0,"area":null},{"id":"2510.24332","title":"Sound Source Localization for Spatial Mapping of Surgical Actions in Dynamic Scenes","created":"2025-10-28","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":"2512.02566","title":"From Panel to Pixel: Zoom-In Vision-Language Pretraining from Biomedical Scientific Literature","created":"2025-12-02","cited_by_count":0,"area":"mllm"},{"id":"2602.24138","title":"Multimodal Optimal Transport for Training-free Temporal Segmentation in Surgical Robotics","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.22583","title":"A vision-language model and platform for temporally mapping surgery from video","created":"2026-03-23","cited_by_count":0,"area":"mllm"},{"id":"2604.20319","title":"SurgCoT: Advancing Spatiotemporal Reasoning in Surgical Videos through a Chain-of-Thought Benchmark","created":"2026-04-22","cited_by_count":0,"area":"lr"},{"id":"2605.26483","title":"Clinically-Grounded Counterfactual Reasoning for Medical Video Diagnosis","created":"2026-05-26","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":"2607.19889","title":"Latent-Action-Guided Video-Language Feature Learning for Surgical Instrument-Tissue Interaction Recognition","created":"2026-07-22","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":"2608.14262","title":"On the Robustness of Temporal Vision-Language Models for Surgical Endoscopy Videos","created":"2026-08-14","cited_by_count":0,"area":"mllm"},{"id":"2608.31065","title":"Multimodal Shared Latent Representation of Narration, Microscope and iOCT Images for Phase Recognition in Vitreoretinal Surgery","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.04555","title":"DART: Depth-as-Target Pretraining for Surgical Vision Foundation Models","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.08543","title":"STSG-VQA: Evidence-Grounded Temporal Question Answering from Surgical Spatio-Temporal Scene Graphs","created":"2026-09-08","cited_by_count":0,"area":"lr"},{"id":"2609.18971","title":"LaSeD: Label-Semantic Self-Distillation for Visual-Only Surgical Phase Recognition","created":"2026-07-16","cited_by_count":0,"area":"distill"},{"id":"2609.27139","title":"A Hierarchy-Aware Video-Language Model Evaluation and Hyperbolic Baseline for Surgery","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31524","title":"Structured Reasoning Agentic Framework for Interpretable Critical View of Safety Assessment","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.31821","title":"A Surgical Foundation Model Reveals Task-Dependent Label Efficiency","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}