{"total":56,"rows":[{"id":"2401.16416","title":"Endo-4DGS: Endoscopic Monocular Scene Reconstruction with 4D Gaussian Splatting","created":"2024-01-29","cited_by_count":43,"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":"2407.19305","title":"GP-VLS: A general-purpose vision language model for surgery","created":"2024-07-27","cited_by_count":17,"area":"mllm"},{"id":"2406.16039","title":"CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery","created":"2024-06-23","cited_by_count":16,"area":null},{"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":"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":"2405.17872","title":"HFGS: 4D Gaussian Splatting with Emphasis on Spatial and Temporal High-Frequency Components for Endoscopic Scene Reconstruction","created":"2024-05-28","cited_by_count":13,"area":null},{"id":"2512.23162","title":"Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling","created":"2025-12-29","cited_by_count":11,"area":"wm"},{"id":"2511.06549","title":"Video Dataset for Surgical Phase, Keypoint, and Instrument Recognition in Laparoscopic Surgery (PhaKIR)","created":"2025-11-09","cited_by_count":9,"area":null},{"id":"2507.16559","title":"Comparative validation of surgical phase recognition, instrument keypoint estimation, and instrument instance segmentation in endoscopy: Results of the PhaKIR 2024 challenge","created":"2025-07-22","cited_by_count":8,"area":null},{"id":"2403.08003","title":"Augmenting Efficient Real-time Surgical Instrument Segmentation in Video with Point Tracking and Segment Anything","created":"2024-03-12","cited_by_count":7,"area":null},{"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":"2405.09806","title":"A Generalist Model for Diverse Text-Guided Medical Image Synthesis","created":"2024-05-16","cited_by_count":6,"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":"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":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4,"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":"2406.15920","title":"SEDMamba: Enhancing Selective State Space Modelling with Bottleneck Mechanism and Fine-to-Coarse Temporal Fusion for Efficient Error Detection in Robot-Assisted Surgery","created":"2024-06-22","cited_by_count":3,"area":"ssm"},{"id":"2503.18755","title":"EgoSurgery-HTS: A Dataset for Egocentric Hand-Tool Segmentation in Open Surgery Videos","created":"2025-03-24","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":"2508.08764","title":"CARES: Collaborative Agentic Reasoning for Error Detection in Surgery","created":"2025-08-12","cited_by_count":3,"area":"agents"},{"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":"2407.19714","title":"Rethinking RGB-D Fusion for Semantic Segmentation in Surgical Datasets","created":"2024-07-29","cited_by_count":2,"area":null},{"id":"2411.07619","title":"Artificial Intelligence for Biomedical Video Generation","created":"2024-11-12","cited_by_count":2,"area":null},{"id":"2509.09327","title":"Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment","created":"2025-09-11","cited_by_count":2,"area":null},{"id":"2603.12430","title":"Surg-R1: A Hierarchical Reasoning Foundation Model for Scalable and Interpretable Surgical Decision Support with Multi-Center Clinical Validation","created":"2026-03-12","cited_by_count":2,"area":"lr"},{"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":"2603.27460","title":"Project Imaging-X: A Survey of 1000+ Open-Access Medical Imaging Datasets for Foundation Model Development","created":"2026-03-29","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":"2410.23962","title":"Image Synthesis with Class-Aware Semantic Diffusion Models for Surgical Scene Segmentation","created":"2024-10-31","cited_by_count":1,"area":"diffusion"},{"id":"2505.09858","title":"Mission Balance: Generating Under-represented Class Samples using Video Diffusion Models","created":"2025-05-14","cited_by_count":1,"area":"diffusion"},{"id":"2506.06830","title":"EndoARSS: Adapting Spatially-Aware Foundation Model for Efficient Activity Recognition and Semantic Segmentation in Endoscopic Surgery","created":"2025-06-07","cited_by_count":1,"area":null},{"id":"2510.07345","title":"Mitigating Surgical Data Imbalance with Dual-Prediction Video Diffusion Model","created":"2025-10-07","cited_by_count":1,"area":"diffusion"},{"id":"2602.12407","title":"MiDAS: A Multimodal Data Acquisition System and Dataset for Robot-Assisted Minimally Invasive Surgery","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2603.29666","title":"CoRe-DA: Contrastive Regression for Unsupervised Domain Adaptation in Surgical Skill Assessment","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2603.29966","title":"Scaling Video Pretraining for Surgical Foundation Models","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.03645","title":"UniSurgSAM: A Unified Promptable Model for Reliable Surgical Video Segmentation","created":"2026-04-04","cited_by_count":1,"area":null},{"id":"2608.08070","title":"SurgWMBench: A Vision-Based Benchmark for World-Modeling Surgical Instrument Motion Planning","created":"2026-08-08","cited_by_count":1,"area":"wm"},{"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":"2504.18756","title":"Multi-Stage Boundary-Aware Transformer Network for Action Segmentation in Untrimmed Surgical Videos","created":"2025-04-26","cited_by_count":0,"area":null},{"id":"2507.19592","title":"SurgPIS: Surgical-instrument-level Instances and Part-level Semantics for Weakly-supervised Part-aware Instance Segmentation","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2603.00108","title":"SurgFusion-Net: Diversified Adaptive Multimodal Fusion Network for Surgical Skill Assessment","created":"2026-02-18","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":"2603.27341","title":"A Comparative Study in Surgical AI: Potential and Limitations of Data, Compute, and Scaling","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.09051","title":"Fine-Grained Action Segmentation for Renorrhaphy in Robot-Assisted Partial Nephrectomy","created":"2026-04-10","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":"2606.23593","title":"Real-Time Multimodal Activity-Aware Error Detection in Robot-Assisted Surgery","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2607.08397","title":"Attribute Retrieving for Open-Vocabulary Endoscopic Compositional Referring Segmentation","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2607.14968","title":"Stitch-Inferencer: Enhance Endoscopic Video Segmentation and Tracking via Panoramic Reconstruction","created":"2026-07-16","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":"2608.16058","title":"SurgVIL: Scaling Surgical Robot Imitation Learning with Open-source Surgical Videos","created":"2026-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2608.17935","title":"Beyond Instrument Motion: Recognizing Tissue Tension Toward Surgical Skill Assessment","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.20284","title":"Towards Surgical World-Action Modeling: A Preliminary Joint Visual-Trajectory Forecasting for Surgical Motion Planning","created":"2026-08-20","cited_by_count":0,"area":"wm"},{"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":"2609.21402","title":"SIRA: Reasoning-Aware Surgical Instrument Segmentation via Query-Anchored Alignment","created":"2026-09-18","cited_by_count":0,"area":null},{"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}