{"list":"other","total":77,"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":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2312.14238","title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","created":"2023-12-21","cited_by_count":2565},{"id":"1412.3555","title":"Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling","created":"2014-12-11","cited_by_count":2367},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"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":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2401.09417","title":"Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model","created":"2024-01-17","cited_by_count":1056},{"id":"1904.03323","title":"Publicly Available Clinical BERT Embeddings","created":"2019-04-06","cited_by_count":1002},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2403.04652","title":"Yi: Open Foundation Models by 01.AI","created":"2024-03-07","cited_by_count":719},{"id":"2401.02954","title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","created":"2024-01-05","cited_by_count":642},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2010.16056","title":"Generating Radiology Reports via Memory-driven Transformer","created":"2020-10-30","cited_by_count":368},{"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":"2106.14463","title":"RadGraph: Extracting Clinical Entities and Relations from Radiology Reports","created":"2021-06-28","cited_by_count":319},{"id":"2106.06963","title":"Exploring and Distilling Posterior and Prior Knowledge for Radiology Report Generation","created":"2021-06-13","cited_by_count":162},{"id":"2311.11045","title":"Orca 2: Teaching Small Language Models How to Reason","created":"2023-11-18","cited_by_count":159},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153},{"id":"2301.02228","title":"MedKLIP: Medical Knowledge Enhanced Language-Image Pre-Training in Radiology","created":"2023-01-05","cited_by_count":149},{"id":"2406.04449","title":"MAIRA-2: Grounded Radiology Report Generation","created":"2024-06-06","cited_by_count":145},{"id":"2010.10042","title":"Improving Factual Completeness and Consistency of Image-to-Text Radiology Report Generation","created":"2020-10-20","cited_by_count":141},{"id":"2304.08295","title":"Interactive and Explainable Region-guided Radiology Report Generation","created":"2023-04-17","cited_by_count":140},{"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},{"id":"2303.10323","title":"Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation","created":"2023-03-18","cited_by_count":118},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"2309.09812","title":"R2GenGPT: Radiology Report Generation with Frozen LLMs","created":"2023-09-18","cited_by_count":114},{"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":"2209.07098","title":"Multi-Modal Masked Autoencoders for Medical Vision-and-Language Pre-Training","created":"2022-09-15","cited_by_count":104},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101},{"id":"2201.09405","title":"Improving Chest X-Ray Report Generation by Leveraging Warm Starting","created":"2022-01-24","cited_by_count":95},{"id":"2308.12604","title":"PromptMRG: Diagnosis-Driven Prompts for Medical Report Generation","created":"2023-08-24","cited_by_count":95},{"id":"2210.12186","title":"Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards","created":"2022-10-21","cited_by_count":83},{"id":"2310.13292","title":"CXR-CLIP: Toward Large Scale Chest X-ray Language-Image Pre-training","created":"2023-10-20","cited_by_count":82},{"id":"2206.14579","title":"Competence-based Multimodal Curriculum Learning for Medical Report Generation","created":"2022-06-24","cited_by_count":76},{"id":"2301.13155","title":"Advancing Radiograph Representation Learning with Masked Record Modeling","created":"2023-01-30","cited_by_count":75},{"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":"2203.10095","title":"AlignTransformer: Hierarchical Alignment of Visual Regions and Disease Tags for Medical Report Generation","created":"2022-03-18","cited_by_count":65},{"id":"2210.12843","title":"Delving into Masked Autoencoders for Multi-Label Thorax Disease Classification","created":"2022-10-23","cited_by_count":65},{"id":"2306.11345","title":"KiUT: Knowledge-injected U-Transformer for Radiology Report Generation","created":"2023-06-20","cited_by_count":62},{"id":"2207.04818","title":"Cross-modal Prototype Driven Network for Radiology Report Generation","created":"2022-07-11","cited_by_count":59},{"id":"2404.09516","title":"State Space Model for New-Generation Network Alternative to Transformers: A Survey","created":"2024-04-15","cited_by_count":59},{"id":"2209.07118","title":"Align, Reason and Learn: Enhancing Medical Vision-and-Language Pre-training with Knowledge","created":"2022-09-15","cited_by_count":51},{"id":"2208.10358","title":"A Medical Semantic-Assisted Transformer for Radiographic Report Generation","created":"2022-08-22","cited_by_count":44},{"id":"2306.06466","title":"ORGAN: Observation-Guided Radiology Report Generation via Tree Reasoning","created":"2023-06-10","cited_by_count":42},{"id":"2109.12242","title":"Weakly Supervised Contrastive Learning for Chest X-Ray Report Generation","created":"2021-09-25","cited_by_count":41},{"id":"2302.08958","title":"Towards Unifying Medical Vision-and-Language Pre-training via Soft Prompts","created":"2023-02-17","cited_by_count":36},{"id":"2306.08749","title":"Utilizing Longitudinal Chest X-Rays and Reports to Pre-Fill Radiology Reports","created":"2023-06-14","cited_by_count":35},{"id":"2107.02104","title":"RATCHET: Medical Transformer for Chest X-ray Diagnosis and Reporting","created":"2021-07-05","cited_by_count":34},{"id":"2407.15158","title":"HERGen: Elevating Radiology Report Generation with Longitudinal Data","created":"2024-07-21","cited_by_count":33},{"id":"2307.09758","title":"Longitudinal Data and a Semantic Similarity Reward for Chest X-Ray Report Generation","created":"2023-07-19","cited_by_count":24},{"id":"2211.01412","title":"CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation","created":"2022-11-02","cited_by_count":22},{"id":"2310.13864","title":"RECAP: Towards Precise Radiology Report Generation via Dynamic Disease Progression Reasoning","created":"2023-10-21","cited_by_count":22},{"id":"2311.02329","title":"Complex Organ Mask Guided Radiology Report Generation","created":"2023-11-04","cited_by_count":22},{"id":"2404.18174","title":"Mamba-FETrack: Frame-Event Tracking via State Space Model","created":"2024-04-28","cited_by_count":22},{"id":"2406.07537","title":"Autoregressive Pretraining with Mamba in Vision","created":"2024-06-11","cited_by_count":22},{"id":"2211.13229","title":"DeltaNet:Conditional Medical Report Generation for COVID-19 Diagnosis","created":"2022-11-12","cited_by_count":13},{"id":"2408.09743","title":"R2GenCSR: Mining Contextual and Residual Information for LLMs-based Radiology Report Generation","created":"2024-08-19","cited_by_count":12},{"id":"2408.10487","title":"MambaEVT: Event Stream based Visual Object Tracking using State Space Model","created":"2024-08-20","cited_by_count":12},{"id":"2304.09185","title":"Token Imbalance Adaptation for Radiology Report Generation","created":"2023-04-18","cited_by_count":10},{"id":"2407.10374","title":"An Empirical Study of Mamba-based Pedestrian Attribute Recognition","created":"2024-07-15","cited_by_count":10},{"id":"2408.03500","title":"e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation","created":"2024-08-07","cited_by_count":10},{"id":"2407.03919","title":"MedRAT: Unpaired Medical Report Generation via Auxiliary Tasks","created":"2024-07-04","cited_by_count":9},{"id":"2404.17926","title":"Pre-training on High Definition X-ray Images: An Experimental Study","created":"2024-04-27","cited_by_count":7}],"next_cursor":null}