{"list":"other","total":63,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"2104.02057","title":"An Empirical Study of Training Self-Supervised Vision Transformers","created":"2021-04-05","cited_by_count":1616},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"2012.07421","title":"WILDS: A Benchmark of in-the-Wild Distribution Shifts","created":"2020-12-14","cited_by_count":1375},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"1802.04712","title":"Attention-based Deep Multiple Instance Learning","created":"2018-02-13","cited_by_count":1095},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2004.09666","title":"Data Efficient and Weakly Supervised Computational Pathology on Whole Slide Images","created":"2020-04-20","cited_by_count":745},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2106.00908","title":"TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification","created":"2021-06-02","cited_by_count":555},{"id":"2011.08939","title":"Dual-stream Multiple Instance Learning Network for Whole Slide Image Classification with Self-supervised Contrastive Learning","created":"2020-11-17","cited_by_count":478},{"id":"2102.03902","title":"Nystr\\\"omformer: A Nystr\\\"om-Based Algorithm for Approximating Self-Attention","created":"2021-02-07","cited_by_count":471},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359},{"id":"2208.06366","title":"BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers","created":"2022-08-12","cited_by_count":303},{"id":"2203.12081","title":"DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification","created":"2022-03-22","cited_by_count":256},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194},{"id":"2009.11169","title":"Whole Slide Images based Cancer Survival Prediction using Attention Guided Deep Multiple Instance Learning Networks","created":"2020-09-23","cited_by_count":178},{"id":"2411.19666","title":"Multimodal Whole Slide Foundation Model for Pathology","created":"2024-11-29","cited_by_count":162},{"id":"2408.00738","title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","created":"2024-08-01","cited_by_count":161},{"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":"2107.13048","title":"Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks","created":"2021-07-27","cited_by_count":124},{"id":"2406.16192","title":"HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis","created":"2024-06-23","cited_by_count":107},{"id":"2303.06873","title":"Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images","created":"2023-03-13","cited_by_count":91},{"id":"2309.07778","title":"Virchow: A Million-Slide Digital Pathology Foundation Model","created":"2023-09-14","cited_by_count":90},{"id":"2403.06800","title":"MambaMIL: Enhancing Long Sequence Modeling with Sequence Reordering in Computational Pathology","created":"2024-03-11","cited_by_count":88},{"id":"2405.11643","title":"Morphological Prototyping for Unsupervised Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":72},{"id":"2402.17228","title":"Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology","created":"2024-02-27","cited_by_count":67},{"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":"2311.07125","title":"Attention-Challenging Multiple Instance Learning for Whole Slide Image Classification","created":"2023-11-13","cited_by_count":61},{"id":"2307.15254","title":"Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image Classification","created":"2023-07-28","cited_by_count":60},{"id":"2206.01794","title":"Additive MIL: Intrinsically Interpretable Multiple Instance Learning for Pathology","created":"2022-06-03","cited_by_count":58},{"id":"2303.08446","title":"Task-specific Fine-tuning via Variational Information Bottleneck for Weakly-supervised Pathology Whole Slide Image Classification","created":"2023-03-15","cited_by_count":54},{"id":"2405.11618","title":"Transcriptomics-guided Slide Representation Learning in Computational Pathology","created":"2024-05-19","cited_by_count":51},{"id":"2410.06424","title":"Restructuring Vector Quantization with the Rotation Trick","created":"2024-10-08","cited_by_count":51},{"id":"2307.04189","title":"Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning","created":"2023-07-09","cited_by_count":47},{"id":"2210.03664","title":"Bi-directional Weakly Supervised Knowledge Distillation for Whole Slide Image Classification","created":"2022-10-07","cited_by_count":43},{"id":"2202.07001","title":"Handcrafted Histological Transformer (H2T): Unsupervised Representation of Whole Slide Images","created":"2022-02-14","cited_by_count":32},{"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":"2402.19326","title":"Generalizable Whole Slide Image Classification with Fine-Grained Visual-Semantic Interaction","created":"2024-02-29","cited_by_count":27},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26},{"id":"2407.03575","title":"DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image Classification","created":"2024-07-04","cited_by_count":25},{"id":"2212.03273","title":"Giga-SSL: Self-Supervised Learning for Gigapixel Images","created":"2022-12-06","cited_by_count":24},{"id":"2312.03558","title":"When an Image is Worth 1,024 x 1,024 Words: A Case Study in Computational Pathology","created":"2023-12-06","cited_by_count":16},{"id":"2303.12214","title":"Prompt-MIL: Boosting Multi-Instance Learning Schemes via Task-specific Prompt Tuning","created":"2023-03-21","cited_by_count":15},{"id":"2210.13007","title":"Iterative Patch Selection for High-Resolution Image Recognition","created":"2022-10-24","cited_by_count":14},{"id":"2410.14195","title":"Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis","created":"2024-10-18","cited_by_count":12},{"id":"2402.06188","title":"A self-supervised framework for learning whole slide representations","created":"2024-02-09","cited_by_count":7},{"id":"2310.01924","title":"RoFormer for Position Aware Multiple Instance Learning in Whole Slide Image Classification","created":"2023-10-03","cited_by_count":4}],"next_cursor":null}