{"list":"other","total":73,"rows":[{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2504.10479","title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","created":"2025-04-14","cited_by_count":1834},{"id":"1612.06890","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","created":"2016-12-20","cited_by_count":1457},{"id":"2205.10625","title":"Least-to-Most Prompting Enables Complex Reasoning in Large Language Models","created":"2022-05-21","cited_by_count":1407},{"id":"2210.03350","title":"Measuring and Narrowing the Compositionality Gap in Language Models","created":"2022-10-07","cited_by_count":1075},{"id":"2403.05525","title":"DeepSeek-VL: Towards Real-World Vision-Language Understanding","created":"2024-03-08","cited_by_count":733},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2503.06749","title":"Vision-R1: Incentivizing Reasoning Capability in Multimodal Large Language Models","created":"2025-03-09","cited_by_count":665},{"id":"2106.05735","title":"The Medical Segmentation Decathlon","created":"2021-06-10","cited_by_count":628},{"id":"2303.08128","title":"ViperGPT: Visual Inference via Python Execution for Reasoning","created":"2023-03-14","cited_by_count":603},{"id":"1901.07042","title":"MIMIC-CXR-JPG, a large publicly available database of labeled chest radiographs","created":"2019-01-21","cited_by_count":597},{"id":"2412.10302","title":"DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding","created":"2024-12-13","cited_by_count":572},{"id":"2210.02406","title":"Decomposed Prompting: A Modular Approach for Solving Complex Tasks","created":"2022-10-05","cited_by_count":558},{"id":"2211.11559","title":"Visual Programming: Compositional visual reasoning without training","created":"2022-11-18","cited_by_count":516},{"id":"2503.01785","title":"Visual-RFT: Visual Reinforcement Fine-Tuning","created":"2025-03-03","cited_by_count":513},{"id":"1901.04056","title":"The Liver Tumor Segmentation Benchmark (LiTS)","created":"2019-01-13","cited_by_count":509},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454},{"id":"2102.09542","title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering","created":"2021-02-18","cited_by_count":449},{"id":"1511.02799","title":"Neural Module Networks","created":"2015-11-09","cited_by_count":376},{"id":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338},{"id":"2307.14334","title":"Towards Generalist Biomedical AI","created":"2023-07-26","cited_by_count":289},{"id":"2403.16999","title":"Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning","created":"2024-03-25","cited_by_count":280},{"id":"2412.18925","title":"HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs","created":"2024-12-25","cited_by_count":265},{"id":"2503.07536","title":"LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL","created":"2025-03-10","cited_by_count":248},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237},{"id":"2412.03555","title":"PaliGemma 2: A Family of Versatile VLMs for Transfer","created":"2024-12-04","cited_by_count":207},{"id":"2403.17834","title":"Generalist Foundation Models from a Multimodal Dataset for 3D Computed Tomography","created":"2024-03-26","cited_by_count":199},{"id":"2402.09181","title":"OmniMedVQA: A New Large-Scale Comprehensive Evaluation Benchmark for Medical LVLM","created":"2024-02-14","cited_by_count":184},{"id":"2502.19634","title":"MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning","created":"2025-02-26","cited_by_count":173},{"id":"1904.00445","title":"The KiTS19 Challenge Data: 300 Kidney Tumor Cases with Clinical Context, CT Semantic Segmentations, and Surgical Outcomes","created":"2019-03-31","cited_by_count":172},{"id":"2404.00578","title":"M3D: Advancing 3D Medical Image Analysis with Multi-Modal Large Language Models","created":"2024-03-31","cited_by_count":162},{"id":"2503.13939","title":"Med-R1: Reinforcement Learning for Generalizable Medical Reasoning in Vision-Language Models","created":"2025-03-18","cited_by_count":144},{"id":"2409.11402","title":"NVLM: Open Frontier-Class Multimodal LLMs","created":"2024-09-17","cited_by_count":125},{"id":"2503.17352","title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","created":"2025-03-21","cited_by_count":124},{"id":"2504.00993","title":"MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs","created":"2025-04-01","cited_by_count":110},{"id":"2403.06801","title":"CT2Rep: Automated Radiology Report Generation for 3D Medical Imaging","created":"2024-03-11","cited_by_count":96},{"id":"2503.07065","title":"Boosting the Generalization and Reasoning of Vision Language Models with Curriculum Reinforcement Learning","created":"2025-03-10","cited_by_count":71},{"id":"2402.19470","title":"Towards Generalizable Tumor Synthesis","created":"2024-02-29","cited_by_count":65},{"id":"2407.16697","title":"AbdomenAtlas: A Large-Scale, Detailed-Annotated, & Multi-Center Dataset for Efficient Transfer Learning and Open Algorithmic Benchmarking","created":"2024-07-23","cited_by_count":65},{"id":"2306.00988","title":"Continual Learning for Abdominal Multi-Organ and Tumor Segmentation","created":"2023-06-01","cited_by_count":43},{"id":"2203.12362","title":"MONAI Label: A framework for AI-assisted Interactive Labeling of 3D Medical Images","created":"2022-03-23","cited_by_count":39},{"id":"2501.04678","title":"RadGPT: Constructing 3D Image-Text Tumor Datasets","created":"2025-01-08","cited_by_count":36},{"id":"2505.16964","title":"MedFrameQA: A Multi-Image Medical VQA Benchmark for Clinical Reasoning","created":"2025-05-22","cited_by_count":34},{"id":"2405.18356","title":"Universal and Extensible Language-Vision Models for Organ Segmentation and Tumor Detection from Abdominal Computed Tomography","created":"2024-05-28","cited_by_count":31},{"id":"2411.03670","title":"Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?","created":"2024-11-06","cited_by_count":31},{"id":"2406.05231","title":"The ULS23 Challenge: a Baseline Model and Benchmark Dataset for 3D Universal Lesion Segmentation in Computed Tomography","created":"2024-06-07","cited_by_count":26},{"id":"2506.11147","title":"3D-RAD: A Comprehensive 3D Radiology Med-VQA Dataset with Multi-Temporal Analysis and Diverse Diagnostic Tasks","created":"2025-06-11","cited_by_count":26},{"id":"2506.11474","title":"Med-PRM: Medical Reasoning Models with Stepwise, Guideline-verified Process Rewards","created":"2025-06-13","cited_by_count":24},{"id":"2605.02240","title":"PhysicianBench: Evaluating LLM Agents in Real-World EHR Environments","created":"2026-05-04","cited_by_count":21},{"id":"2109.12265","title":"Label-Assemble: Leveraging Multiple Datasets with Partial Labels","created":"2021-09-25","cited_by_count":20},{"id":"2308.03008","title":"Early Detection and Localization of Pancreatic Cancer by Label-Free Tumor Synthesis","created":"2023-08-06","cited_by_count":17},{"id":"2507.01291","title":"PanTS: The Pancreatic Tumor Segmentation Dataset","created":"2025-07-02","cited_by_count":16},{"id":"2505.18915","title":"Are Vision Language Models Ready for Clinical Diagnosis? A 3D Medical Benchmark for Tumor-centric Visual Question Answering","created":"2025-05-25","cited_by_count":14},{"id":"2510.14831","title":"Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data","created":"2025-10-16","cited_by_count":13},{"id":"2506.09958","title":"Kvasir-VQA-x1: A Multimodal Dataset for Medical Reasoning and Robust MedVQA in Gastrointestinal Endoscopy","created":"2025-06-11","cited_by_count":11},{"id":"2507.05582","title":"Learning Segmentation from Radiology Reports","created":"2025-07-08","cited_by_count":11},{"id":"2310.15098","title":"Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data","created":"2023-10-23","cited_by_count":9},{"id":"2402.19423","title":"Leveraging AI Predicted and Expert Revised Annotations in Interactive Segmentation: Continual Tuning or Full Training?","created":"2024-02-29","cited_by_count":9},{"id":"2407.04687","title":"Embracing Massive Medical Data","created":"2024-07-05","cited_by_count":9},{"id":"2510.14803","title":"Scaling Artificial Intelligence for Multi-Tumor Early Detection with More Reports, Fewer Masks","created":"2025-10-16","cited_by_count":9},{"id":"2411.02753","title":"Label Critic: Design Data Before Models","created":"2024-11-05","cited_by_count":4},{"id":"2505.20021","title":"Decomposing Complex Visual Comprehension into Atomic Visual Skills for Vision Language Models","created":"2025-05-26","cited_by_count":4},{"id":"2601.22134","title":"Early and Prediagnostic Detection of Pancreatic Cancer from Computed Tomography","created":"2026-01-29","cited_by_count":4},{"id":"2512.19091","title":"Auditing Significance, Metric Choice, and Demographic Fairness in Medical AI Challenges","created":"2025-12-22","cited_by_count":2},{"id":"2601.14406","title":"Large-Scale Label Quality Assessment for Medical Segmentation via a Vision-Language Judge and Synthetic Data","created":"2026-01-20","cited_by_count":2},{"id":"2604.26288","title":"CheXthought: A global multimodal dataset of clinical chain-of-thought reasoning and visual attention for chest X-ray interpretation","created":"2026-04-29","cited_by_count":2}],"next_cursor":null}