{"total":15,"rows":[{"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":"2505.15206","title":"EndoVLA: Dual-Phase Vision-Language-Action Model for Autonomous Tracking in Endoscopy","created":"2025-05-21","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":"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":"2504.19918","title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","created":"2025-04-28","cited_by_count":2,"area":null},{"id":"2507.15094","title":"BleedOrigin: Dynamic Bleeding Source Localization in Endoscopic Submucosal Dissection via Dual-Stage Detection and Tracking","created":"2025-07-20","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":"2603.29962","title":"SurgTEMP: Temporal-Aware Surgical Video Question Answering with Text-guided Visual Memory for Laparoscopic Cholecystectomy","created":"2026-03-31","cited_by_count":1,"area":null},{"id":"2604.01915","title":"Enhancing Medical Visual Grounding via Knowledge-guided Spatial Prompts","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2605.11208","title":"Hi-GaTA: Hierarchical Gated Temporal Aggregation Adapter for Surgical Video Report Generation","created":"2026-05-11","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":"2607.27122","title":"Towards Grounded GI Endoscopy VQA via Multi-Task Learning on Small VLMs","created":"2026-07-29","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}