{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2410.21276","title":"GPT-4o System Card","created":"2024-10-25","cited_by_count":4588},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2308.12966","title":"Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond","created":"2023-08-24","cited_by_count":2224},{"id":"2306.00890","title":"LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day","created":"2023-06-01","cited_by_count":1305},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"2205.08534","title":"Vision Transformer Adapter for Dense Predictions","created":"2022-05-17","cited_by_count":565},{"id":"2003.10286","title":"PathVQA: 30000+ Questions for Medical Visual Question Answering","created":"2020-03-07","cited_by_count":475},{"id":"1806.03962","title":"Rotation Equivariant CNNs for Digital Pathology","created":"2018-06-08","cited_by_count":422},{"id":"2403.17297","title":"InternLM2 Technical Report","created":"2024-03-26","cited_by_count":397},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"2305.10415","title":"PMC-VQA: Visual Instruction Tuning for Medical Visual Question Answering","created":"2023-05-17","cited_by_count":338},{"id":"1911.04623","title":"SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learning","created":"2019-11-12","cited_by_count":195},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194},{"id":"1912.12378","title":"Deep neural network models for computational histopathology: A survey","created":"2019-12-28","cited_by_count":165},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162},{"id":"2212.04690","title":"Benchmarking Self-Supervised Learning on Diverse Pathology Datasets","created":"2022-12-09","cited_by_count":150},{"id":"2306.07831","title":"Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images","created":"2023-06-13","cited_by_count":134},{"id":"2111.04740","title":"BRACS: A Dataset for BReAst Carcinoma Subtyping in H&E Histology Images","created":"2021-11-08","cited_by_count":132},{"id":"2306.15350","title":"CellViT: Vision Transformers for Precise Cell Segmentation and Classification","created":"2023-06-27","cited_by_count":108},{"id":"1912.12142","title":"Lung and Colon Cancer Histopathological Image Dataset (LC25000)","created":"2019-12-16","cited_by_count":89},{"id":"2312.04746","title":"Quilt-LLaVA: Visual Instruction Tuning by Extracting Localized Narratives from Open-Source Histopathology Videos","created":"2023-12-07","cited_by_count":86},{"id":"2405.10254","title":"PRISM: A Multi-Modal Generative Foundation Model for Slide-Level Histopathology","created":"2024-05-16","cited_by_count":85},{"id":"2409.09173","title":"Phikon-v2, A large and public feature extractor for biomarker prediction","created":"2024-09-13","cited_by_count":74},{"id":"2403.07719","title":"Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis","created":"2024-03-12","cited_by_count":67},{"id":"2101.12355","title":"A Petri Dish for Histopathology Image Analysis","created":"2021-01-29","cited_by_count":64},{"id":"2305.15072","title":"PathAsst: A Generative Foundation AI Assistant Towards Artificial General Intelligence of Pathology","created":"2023-05-24","cited_by_count":57},{"id":"2410.11761","title":"SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding","created":"2024-10-15","cited_by_count":57},{"id":"2006.12230","title":"HookNet: multi-resolution convolutional neural networks for semantic segmentation in histopathology whole-slide images","created":"2020-06-22","cited_by_count":45},{"id":"2401.16355","title":"PathMMU: A Massive Multimodal Expert-Level Benchmark for Understanding and Reasoning in Pathology","created":"2024-01-29","cited_by_count":43},{"id":"2403.05396","title":"HistGen: Histopathology Report Generation via Local-Global Feature Encoding and Cross-modal Context Interaction","created":"2024-03-08","cited_by_count":43},{"id":"2107.00272","title":"A Survey on Graph-Based Deep Learning for Computational Histopathology","created":"2021-07-01","cited_by_count":41},{"id":"2305.17891","title":"The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification","created":"2023-05-29","cited_by_count":41},{"id":"2401.04079","title":"RudolfV: A Foundation Model by Pathologists for Pathologists","created":"2024-01-08","cited_by_count":41},{"id":"2205.09723","title":"Robust and Efficient Medical Imaging with Self-Supervision","created":"2022-05-19","cited_by_count":40},{"id":"2412.02141","title":"WSI-LLaVA: A Multimodal Large Language Model for Whole Slide Image","created":"2024-12-03","cited_by_count":40},{"id":"2204.06455","title":"WSSS4LUAD: Grand Challenge on Weakly-supervised Tissue Semantic Segmentation for Lung Adenocarcinoma","created":"2022-04-13","cited_by_count":36},{"id":"2407.05603","title":"WSI-VQA: Interpreting Whole Slide Images by Generative Visual Question Answering","created":"2024-07-08","cited_by_count":34},{"id":"2412.12077","title":"CPath-Omni: A Unified Multimodal Foundation Model for Patch and Whole Slide Image Analysis in Computational Pathology","created":"2024-12-16","cited_by_count":34},{"id":"2311.16480","title":"WsiCaption: Multiple Instance Generation of Pathology Reports for Gigapixel Whole-Slide Images","created":"2023-11-27","cited_by_count":31},{"id":"2304.05482","title":"Computational Pathology: A Survey Review and The Way Forward","created":"2023-04-11","cited_by_count":30},{"id":"2502.08391","title":"ViLa-MIL: Dual-scale Vision-Language Multiple Instance Learning for Whole Slide Image Classification","created":"2025-02-12","cited_by_count":28},{"id":"2010.16380","title":"Development and Evaluation of a Deep Neural Network for Histologic Classification of Renal Cell Carcinoma on Biopsy and Surgical Resection Slides","created":"2020-10-30","cited_by_count":24},{"id":"2411.14743","title":"FOCUS: Knowledge-enhanced Adaptive Visual Compression for Few-shot Whole Slide Image Classification","created":"2024-11-22","cited_by_count":20},{"id":"2309.07400","title":"HIGT: Hierarchical Interaction Graph-Transformer for Whole Slide Image Analysis","created":"2023-09-14","cited_by_count":17},{"id":"2412.03748","title":"HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution","created":"2024-12-04","cited_by_count":17},{"id":"2105.10420","title":"Self-learning for weakly supervised Gleason grading of local patterns","created":"2021-05-21","cited_by_count":14},{"id":"2404.09942","title":"Knowledge-enhanced Visual-Language Pretraining for Computational Pathology","created":"2024-04-15","cited_by_count":14},{"id":"2004.06684","title":"Multi-Resolution A*","created":"2020-04-14","cited_by_count":13},{"id":"2411.07660","title":"HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image Classification","created":"2024-11-12","cited_by_count":13},{"id":"2504.18856","title":"Multi-Resolution Pathology-Language Pre-training Model with Text-Guided Visual Representation","created":"2025-04-26","cited_by_count":6}],"next_cursor":null}