{"total":59,"rows":[{"id":"2403.02469","title":"Vision-Language Models for Medical Report Generation and Visual Question Answering: A Review","created":"2024-03-04","cited_by_count":125,"area":"mllm"},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"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,"area":null},{"id":"2305.11692","title":"Surgical-VQLA: Transformer with Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-05-19","cited_by_count":44,"area":null},{"id":"2312.10251","title":"Advancing Surgical VQA with Scene Graph Knowledge","created":"2023-12-15","cited_by_count":41,"area":null},{"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,"area":"mllm"},{"id":"2501.11347","title":"EndoChat: Grounded Multimodal Large Language Model for Endoscopic Surgery","created":"2025-01-20","cited_by_count":37,"area":"mllm"},{"id":"2408.07981","title":"LLaVA-Surg: Towards Multimodal Surgical Assistant via Structured Surgical Video Learning","created":"2024-08-15","cited_by_count":34,"area":"mllm"},{"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":"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":"2409.01437","title":"Kvasir-VQA: A Text-Image Pair GI Tract Dataset","created":"2024-09-02","cited_by_count":23,"area":null},{"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,"area":null},{"id":"2307.05182","title":"CAT-ViL: Co-Attention Gated Vision-Language Embedding for Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-11","cited_by_count":17,"area":null},{"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":"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":"2504.14692","title":"OmniV-Med: Scaling Medical Vision-Language Model for Universal Visual Understanding","created":"2025-04-20","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":"2307.12045","title":"Revisiting Distillation for Continual Learning on Visual Question Localized-Answering in Robotic Surgery","created":"2023-07-22","cited_by_count":15,"area":null},{"id":"2310.16033","title":"Towards Perceiving Small Visual Details in Zero-shot Visual Question Answering with Multimodal LLMs","created":"2023-10-24","cited_by_count":15,"area":"mllm"},{"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,"area":"mllm"},{"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":"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":"2307.12626","title":"Enhancing Human-like Multi-Modal Reasoning: A New Challenging Dataset and Comprehensive Framework","created":"2023-07-24","cited_by_count":11,"area":"lr"},{"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":"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":"2511.03325","title":"SurgViVQA: Temporally-Grounded Video Question Answering for Surgical Scene Understanding","created":"2025-11-05","cited_by_count":7,"area":null},{"id":"2411.10937","title":"Memory-Augmented Multimodal LLMs for Surgical VQA via Self-Contained Inquiry","created":"2024-11-17","cited_by_count":6,"area":"mllm"},{"id":"2401.08256","title":"Multitask Learning in Minimally Invasive Surgical Vision: A Review","created":"2024-01-16","cited_by_count":5,"area":null},{"id":"2502.02438","title":"Medical Multimodal Model Stealing Attacks via Adversarial Domain Alignment","created":"2025-02-04","cited_by_count":5,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","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":"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":"2511.21339","title":"SurgMLLMBench: A Multimodal Large Language Model Benchmark Dataset for Surgical Scene Understanding","created":"2025-11-26","cited_by_count":3,"area":"mllm"},{"id":"2601.12224","title":"Where It Moves, It Matters: Referring Surgical Instrument Segmentation via Motion","created":"2026-01-18","cited_by_count":3,"area":null},{"id":"2306.16285","title":"Generalizing Surgical Instruments Segmentation to Unseen Domains with One-to-Many Synthesis","created":"2023-06-28","cited_by_count":2,"area":null},{"id":"2503.18536","title":"DiN: Diffusion Model for Robust Medical VQA with Semantic Noisy Labels","created":"2025-03-24","cited_by_count":2,"area":"diffusion"},{"id":"2508.21430","title":"Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models","created":"2025-08-29","cited_by_count":2,"area":"mllm"},{"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":"2605.01911","title":"SurgCheck: Do Vision-Language Models Really Look at Images in Surgical VQA?","created":"2026-05-03","cited_by_count":2,"area":"mllm"},{"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":"2604.00784","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":"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":"2509.17429","title":"Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration","created":"2025-09-22","cited_by_count":0,"area":"agents"},{"id":"2511.01357","title":"CMI-MTL: Cross-Mamba interaction based multi-task learning for medical visual question answering","created":"2025-11-03","cited_by_count":0,"area":"ssm"},{"id":"2511.03178","title":"SurgAnt-ViVQA: Learning to Anticipate Surgical Events through GRU-Driven Temporal Cross-Attention","created":"2025-11-05","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":"2512.05740","title":"Distilling Expert Surgical Knowledge: How to train local surgical VLMs for anatomy explanation in Complete Mesocolic Excision","created":"2025-12-05","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":"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":"2604.20319","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":"2605.17915","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":"2606.15861","title":"Object Tokens as a Bridge Between Segmentation and Visual Question Answering in Robotic Surgery","created":"2026-06-14","cited_by_count":0,"area":"mllm"},{"id":"2607.01751","title":"MedStreamBench: A Time-Aware Benchmark for Streaming and Proactive Medical Video Understanding","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.01473","title":"Slot2Text: Object-Centric Visual Tokenization for Efficient and Spatially Traceable Surgical MLLMs","created":"2026-08-02","cited_by_count":0,"area":"mllm"},{"id":"2609.06914","title":"A visual large language foundational model for medical image recognition using clinician-contributed online resources","created":"2026-09-07","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"}],"next_cursor":null}