{"list":"other","total":57,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"1506.01497","title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks","created":"2015-06-04","cited_by_count":9639},{"id":"2402.03300","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","created":"2024-02-05","cited_by_count":9379},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"1506.02640","title":"You Only Look Once: Unified, Real-Time Object Detection","created":"2015-06-08","cited_by_count":4852},{"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":"2109.01652","title":"Finetuned Language Models Are Zero-Shot Learners","created":"2021-09-03","cited_by_count":3780},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2212.10560","title":"Self-Instruct: Aligning Language Models with Self-Generated Instructions","created":"2022-12-20","cited_by_count":2724},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719},{"id":"2212.13138","title":"Large Language Models Encode Clinical Knowledge","created":"2022-12-26","cited_by_count":1830},{"id":"1901.07031","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","created":"2019-01-21","cited_by_count":1423},{"id":"2312.07533","title":"VILA: On Pre-training for Visual Language Models","created":"2023-12-12","cited_by_count":692},{"id":"2304.03277","title":"Instruction Tuning with GPT-4","created":"2023-04-06","cited_by_count":686},{"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":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2309.11998","title":"LMSYS-Chat-1M: A Large-Scale Real-World LLM Conversation Dataset","created":"2023-09-21","cited_by_count":461},{"id":"2204.09817","title":"Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing","created":"2022-04-21","cited_by_count":339},{"id":"2004.09167","title":"CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT","created":"2020-04-20","cited_by_count":337},{"id":"2405.02246","title":"What matters when building vision-language models?","created":"2024-05-03","cited_by_count":326},{"id":"2106.14463","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","created":"2021-06-28","cited_by_count":319},{"id":"1901.07441","title":"PadChest: A large chest x-ray image dataset with multi-label annotated reports","created":"2019-01-22","cited_by_count":309},{"id":"2012.15029","title":"VinDr-CXR: An open dataset of chest X-rays with radiologist's annotations","created":"2020-12-30","cited_by_count":239},{"id":"2404.18416","title":"Capabilities of Gemini Models in Medicine","created":"2024-04-29","cited_by_count":237},{"id":"2405.07960","title":"AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments","created":"2024-05-13","cited_by_count":231},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173},{"id":"2406.04449","title":"MAIRA-2: Grounded Radiology Report Generation","created":"2024-06-06","cited_by_count":145},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140},{"id":"2405.03595","title":"GREEN: Generative Radiology Report Evaluation and Error Notation","created":"2024-05-06","cited_by_count":128},{"id":"2405.19538","title":"CheXpert Plus: Augmenting a Large Chest X-ray Dataset with Text Radiology Reports, Patient Demographics and Additional Image Formats","created":"2024-05-29","cited_by_count":106},{"id":"2404.07973","title":"Ferret-v2: An Improved Baseline for Referring and Grounding with Large Language Models","created":"2024-04-11","cited_by_count":97},{"id":"2108.00316","title":"Chest ImaGenome Dataset for Clinical Reasoning","created":"2021-07-31","cited_by_count":90},{"id":"2405.03162","title":"Advancing Multimodal Medical Capabilities of Gemini","created":"2024-05-06","cited_by_count":90},{"id":"2103.08700","title":"Deep Learning for Chest X-ray Analysis: A Survey","created":"2021-03-15","cited_by_count":84},{"id":"2210.12186","title":"Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards","created":"2022-10-21","cited_by_count":83},{"id":"2401.12208","title":"A Vision-Language Foundation Model to Enhance Efficiency of Chest X-ray Interpretation","created":"2024-01-22","cited_by_count":81},{"id":"2401.05654","title":"Towards Conversational Diagnostic AI","created":"2024-01-11","cited_by_count":79},{"id":"2112.15011","title":"Radiology Report Generation with a Learned Knowledge Base and Multi-modal Alignment","created":"2021-12-30","cited_by_count":73},{"id":"2204.07156","title":"Any-resolution Training for High-resolution Image Synthesis","created":"2022-04-14","cited_by_count":72},{"id":"2211.05719","title":"MMDialog: A Large-scale Multi-turn Dialogue Dataset Towards Multi-modal Open-domain Conversation","created":"2022-11-10","cited_by_count":56},{"id":"2102.09777","title":"Progressive Transformer-Based Generation of Radiology Reports","created":"2021-02-19","cited_by_count":43},{"id":"2411.05085","title":"PadChest-GR: A Bilingual Chest X-ray Dataset for Grounded Radiology Report Generation","created":"2024-11-07","cited_by_count":35},{"id":"2411.15122","title":"ReXrank: A Public Leaderboard for AI-Powered Radiology Report Generation","created":"2024-11-22","cited_by_count":25},{"id":"2404.15770","title":"ChEX: Interactive Localization and Region Description in Chest X-rays","created":"2024-04-24","cited_by_count":19},{"id":"2006.00730","title":"Automatic classification between COVID-19 pneumonia, non-COVID-19 pneumonia, and the healthy on chest X-ray image: combination of data augmentation methods","created":"2020-06-01","cited_by_count":9},{"id":"2408.11556","title":"Understanding Data Movement in Tightly Coupled Heterogeneous Systems: A Case Study with the Grace Hopper Superchip","created":"2024-08-21","cited_by_count":8},{"id":"2311.16764","title":"Radiology-Aware Model-Based Evaluation Metric for Report Generation","created":"2023-11-28","cited_by_count":7},{"id":"2306.13813","title":"DualAttNet: Synergistic Fusion of Image-level and Fine-Grained Disease Attention for Multi-Label Lesion Detection in Chest X-rays","created":"2023-06-23","cited_by_count":5},{"id":"2305.04561","title":"Boosting Radiology Report Generation by Infusing Comparison Prior","created":"2023-05-08","cited_by_count":3}],"next_cursor":null}