{"list":"other","total":62,"rows":[{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2601.03267","title":"OpenAI GPT-5 System Card","created":"2025-12-19","cited_by_count":989},{"id":"1806.01768","title":"Evidential Deep Learning to Quantify Classification Uncertainty","created":"2018-06-05","cited_by_count":732},{"id":"1602.03012","title":"EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos","created":"2016-02-09","cited_by_count":367},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162},{"id":"2109.03223","title":"Rendezvous: Attention Mechanisms for the Recognition of Surgical Action Triplets in Endoscopic Videos","created":"2021-09-07","cited_by_count":141},{"id":"2208.02049","title":"AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy","created":"2022-08-03","cited_by_count":85},{"id":"2306.16741","title":"Foundation Model for Endoscopy Video Analysis via Large-scale Self-supervised Pre-train","created":"2023-06-29","cited_by_count":75},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68},{"id":"2007.05405","title":"Recognition of Instrument-Tissue Interactions in Endoscopic Videos via Action Triplets","created":"2020-07-10","cited_by_count":66},{"id":"2109.14956","title":"Comparative Validation of Machine Learning Algorithms for Surgical Workflow and Skill Analysis with the HeiChole Benchmark","created":"2021-09-30","cited_by_count":60},{"id":"2206.11053","title":"Surgical-VQA: Visual Question Answering in Surgical Scenes using Transformer","created":"2022-06-22","cited_by_count":59},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56},{"id":"2401.11174","title":"Pixel-Wise Recognition for Holistic Surgical Scene Understanding","created":"2024-01-20","cited_by_count":49},{"id":"2304.09974","title":"SurgicalGPT: End-to-End Language-Vision GPT for Visual Question Answering in Surgery","created":"2023-04-19","cited_by_count":48},{"id":"2005.03501","title":"Heidelberg Colorectal Data Set for Surgical Data Science in the Sensor Operating Room","created":"2020-05-07","cited_by_count":47},{"id":"2405.10075","title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","created":"2024-05-16","cited_by_count":42},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41},{"id":"2312.11250","title":"Challenges in Multi-centric Generalization: Phase and Step Recognition in Roux-en-Y Gastric Bypass Surgery","created":"2023-12-18","cited_by_count":40},{"id":"2405.10948","title":"Surgical-LVLM: Learning to Adapt Large Vision-Language Model for Grounded Visual Question Answering in Robotic Surgery","created":"2024-03-22","cited_by_count":39},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39},{"id":"2104.03178","title":"The SARAS Endoscopic Surgeon Action Detection (ESAD) dataset: Challenges and methods","created":"2021-04-07","cited_by_count":38},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34},{"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},{"id":"2403.05949","title":"General surgery vision transformer: A video pre-trained foundation model for general surgery","created":"2024-03-09","cited_by_count":25},{"id":"2501.09436","title":"Scaling up self-supervised learning for improved surgical foundation models","created":"2025-01-16","cited_by_count":25},{"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},{"id":"2312.12429","title":"The Endoscapes Dataset for Surgical Scene Segmentation, Object Detection, and Critical View of Safety Assessment: Official Splits and Benchmark","created":"2023-12-19","cited_by_count":21},{"id":"2402.16664","title":"LLM-Assisted Multi-Teacher Continual Learning for Visual Question Answering in Robotic Surgery","created":"2024-02-26","cited_by_count":20},{"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},{"id":"2406.16039","title":"CholecInstanceSeg: A Tool Instance Segmentation Dataset for Laparoscopic Surgery","created":"2024-06-23","cited_by_count":16},{"id":"2509.10555","title":"SurgLaVi: Large-Scale Hierarchical Dataset for Surgical Vision-Language Representation Learning","created":"2025-09-09","cited_by_count":16},{"id":"2410.07540","title":"CoPESD: A Multi-Level Surgical Motion Dataset for Training Large Vision-Language Models to Co-Pilot Endoscopic Submucosal Dissection","created":"2024-10-10","cited_by_count":15},{"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},{"id":"2302.03022","title":"SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery","created":"2023-02-06","cited_by_count":14},{"id":"2505.23601","title":"EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis","created":"2025-05-29","cited_by_count":14},{"id":"2202.13402","title":"Concept Graph Neural Networks for Surgical Video Understanding","created":"2022-02-27","cited_by_count":13},{"id":"2410.09750","title":"Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models","created":"2024-10-13","cited_by_count":13},{"id":"2506.17873","title":"SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model","created":"2025-06-22","cited_by_count":13},{"id":"2511.01775","title":"How Far Are Surgeons from Surgical World Models? A Pilot Study on Zero-shot Surgical Video Generation with Expert Assessment","created":"2025-11-03","cited_by_count":11},{"id":"2512.23162","title":"Cosmos-H-Surgical: Learning Surgical Robot Policies from Videos via World Modeling","created":"2025-12-29","cited_by_count":11},{"id":"2506.02692","title":"Large-scale Self-supervised Video Foundation Model for Intelligent Surgery","created":"2025-06-03","cited_by_count":10},{"id":"2506.07603","title":"SurgBench: A Unified Large-Scale Benchmark for Surgical Video Analysis","created":"2025-06-09","cited_by_count":9},{"id":"2412.16078","title":"SegCol Challenge: Semantic Segmentation for Tools and Fold Edges in Colonoscopy data","created":"2024-12-20","cited_by_count":7},{"id":"2603.06570","title":"SUREON: A Benchmark and Vision-Language-Model for Surgical Reasoning","created":"2026-03-06","cited_by_count":7},{"id":"2505.10764","title":"SurgXBench: Explainable Vision-Language Model Benchmark for Surgery","created":"2025-05-16","cited_by_count":6},{"id":"2509.17100","title":"The SAGES Critical View of Safety Challenge: A Global Benchmark for AI-Assisted Surgical Quality Assessment","created":"2025-09-21","cited_by_count":6},{"id":"2501.00525","title":"Systematic Evaluation and Guidelines for Segment Anything Model in Surgical Video Analysis","created":"2024-12-31","cited_by_count":5},{"id":"2504.02799","title":"Systematic Evaluation of Large Vision-Language Models for Surgical Artificial Intelligence","created":"2025-04-03","cited_by_count":5},{"id":"2506.01130","title":"ProstaTD: Bridging Surgical Triplet from Classification to Fully Supervised Detection","created":"2025-06-01","cited_by_count":4},{"id":"2602.05638","title":"SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos","created":"2026-02-05","cited_by_count":4},{"id":"2511.21339","title":"SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding","created":"2025-11-26","cited_by_count":3},{"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},{"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},{"id":"2602.21706","title":"SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video","created":"2026-02-25","cited_by_count":1}],"next_cursor":null}