{"total":422,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744,"area":"wm"},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681,"area":null},{"id":"2304.00685","title":"Vision-Language Models for Vision Tasks: A Survey","created":"2023-04-03","cited_by_count":839,"area":"mllm"},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798,"area":null},{"id":"2106.05974","title":"Scaling Vision with Sparse Mixture of Experts","created":"2021-06-10","cited_by_count":747,"area":"moe"},{"id":"2112.04482","title":"FLAVA: A Foundational Language And Vision Alignment Model","created":"2021-12-08","cited_by_count":649,"area":null},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644,"area":"diffusion"},{"id":"2303.00915","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","created":"2023-03-02","cited_by_count":520,"area":null},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436,"area":null},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2306.11207","title":"Quilt-1M: One Million Image-Text Pairs for Histopathology","created":"2023-06-20","cited_by_count":194,"area":null},{"id":"2111.10050","title":"Combined Scaling for Zero-shot Transfer Learning","created":"2021-11-19","cited_by_count":182,"area":null},{"id":"2408.00738","title":"Virchow2: Scaling Self-Supervised Mixed Magnification Models in Pathology","created":"2024-08-01","cited_by_count":161,"area":null},{"id":"2212.00638","title":"Finetune like you pretrain: Improved finetuning of zero-shot vision models","created":"2022-12-01","cited_by_count":150,"area":null},{"id":"2212.04690","title":"Benchmarking Self-Supervised Learning on Diverse Pathology Datasets","created":"2022-12-09","cited_by_count":150,"area":null},{"id":"2412.00081","title":"Task Singular Vectors: Reducing Task Interference in Model Merging","created":"2024-11-26","cited_by_count":147,"area":null},{"id":"2204.08790","title":"ELEVATER: A Benchmark and Toolkit for Evaluating Language-Augmented Visual Models","created":"2022-04-19","cited_by_count":141,"area":null},{"id":"2107.07002","title":"The Benchmark Lottery","created":"2021-07-14","cited_by_count":136,"area":null},{"id":"2206.04673","title":"Neural Prompt Search","created":"2022-06-09","cited_by_count":135,"area":null},{"id":"2212.03145","title":"FacT: Factor-Tuning for Lightweight Adaptation on Vision Transformer","created":"2022-12-06","cited_by_count":133,"area":null},{"id":"2405.07813","title":"Localizing Task Information for Improved Model Merging and Compression","created":"2024-05-13","cited_by_count":131,"area":null},{"id":"2207.07039","title":"Convolutional Bypasses Are Better Vision Transformer Adapters","created":"2022-07-14","cited_by_count":121,"area":null},{"id":"2402.12336","title":"Robust CLIP: Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models","created":"2024-02-19","cited_by_count":120,"area":"mllm"},{"id":"2212.07016","title":"Understanding Zero-Shot Adversarial Robustness for Large-Scale Models","created":"2022-12-14","cited_by_count":117,"area":"mllm"},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115,"area":null},{"id":"2211.01335","title":"Chinese CLIP: Contrastive Vision-Language Pretraining in Chinese","created":"2022-11-02","cited_by_count":109,"area":"mllm"},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2406.16192","title":"HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis","created":"2024-06-23","cited_by_count":107,"area":null},{"id":"2203.15046","title":"AUC Maximization in the Era of Big Data and AI: A Survey","created":"2022-03-28","cited_by_count":100,"area":null},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99,"area":null},{"id":"2208.05516","title":"Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP","created":"2022-08-10","cited_by_count":97,"area":null},{"id":"2502.04959","title":"No Task Left Behind: Isotropic Model Merging with Common and Task-Specific Subspaces","created":"2025-02-07","cited_by_count":96,"area":null},{"id":"2309.07778","title":"Virchow: A Million-Slide Digital Pathology Foundation Model","created":"2023-09-14","cited_by_count":90,"area":null},{"id":"2210.16156","title":"Reliability of CKA as a Similarity Measure in Deep Learning","created":"2022-10-28","cited_by_count":87,"area":null},{"id":"2211.06679","title":"AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities","created":"2022-11-12","cited_by_count":85,"area":null},{"id":"2201.03529","title":"Head2Toe: Utilizing Intermediate Representations for Better Transfer Learning","created":"2022-01-10","cited_by_count":83,"area":null},{"id":"2203.16329","title":"Parameter-efficient Model Adaptation for Vision Transformers","created":"2022-03-29","cited_by_count":81,"area":null},{"id":"2202.08360","title":"Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision","created":"2022-02-16","cited_by_count":80,"area":null},{"id":"2204.09222","title":"K-LITE: Learning Transferable Visual Models with External Knowledge","created":"2022-04-20","cited_by_count":79,"area":null},{"id":"2308.08428","title":"ALIP: Adaptive Language-Image Pre-training with Synthetic Caption","created":"2023-08-16","cited_by_count":70,"area":null},{"id":"2310.07699","title":"VeCLIP: Improving CLIP Training via Visual-enriched Captions","created":"2023-10-11","cited_by_count":70,"area":"mllm"},{"id":"2101.12355","title":"A Petri Dish for Histopathology Image Analysis","created":"2021-01-29","cited_by_count":64,"area":null},{"id":"2203.01825","title":"What Makes Transfer Learning Work For Medical Images: Feature Reuse & Other Factors","created":"2022-03-02","cited_by_count":61,"area":null},{"id":"2306.11925","title":"LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching","created":"2023-06-20","cited_by_count":60,"area":"mllm"},{"id":"2301.07094","title":"Learning Customized Visual Models with Retrieval-Augmented Knowledge","created":"2023-01-17","cited_by_count":58,"area":"rag"},{"id":"2210.02984","title":"The Lie Derivative for Measuring Learned Equivariance","created":"2022-10-06","cited_by_count":54,"area":null},{"id":"2106.10800","title":"Lossy Compression for Lossless Prediction","created":"2021-06-21","cited_by_count":52,"area":null},{"id":"2309.00748","title":"PathLDM: Text conditioned Latent Diffusion Model for Histopathology","created":"2023-09-01","cited_by_count":52,"area":"diffusion"},{"id":"2410.23179","title":"Does equivariance matter at scale?","created":"2024-10-30","cited_by_count":52,"area":null},{"id":"2211.11720","title":"Multitask Vision-Language Prompt Tuning","created":"2022-11-21","cited_by_count":51,"area":"mllm"},{"id":"2406.04303","title":"Vision-LSTM: xLSTM as Generic Vision Backbone","created":"2024-06-06","cited_by_count":51,"area":null},{"id":"2303.13199","title":"First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning","created":"2023-03-23","cited_by_count":46,"area":null},{"id":"2110.10211","title":"Learning Partial Equivariances from Data","created":"2021-10-19","cited_by_count":45,"area":null},{"id":"2307.16867","title":"Revisiting the Parameter Efficiency of Adapters from the Perspective of Precision Redundancy","created":"2023-07-31","cited_by_count":44,"area":null},{"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,"area":"mllm"},{"id":"2401.04079","title":"RudolfV: A Foundation Model by Pathologists for Pathologists","created":"2024-01-08","cited_by_count":41,"area":null},{"id":"2410.17146","title":"LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging","created":"2024-10-22","cited_by_count":41,"area":null},{"id":"2312.10136","title":"Gradient-based Parameter Selection for Efficient Fine-Tuning","created":"2023-12-15","cited_by_count":40,"area":null},{"id":"2404.02132","title":"ViTamin: Designing Scalable Vision Models in the Vision-Language Era","created":"2024-04-02","cited_by_count":39,"area":"mllm"},{"id":"2203.00077","title":"One Model is All You Need: Multi-Task Learning Enables Simultaneous Histology Image Segmentation and Classification","created":"2022-02-28","cited_by_count":38,"area":null},{"id":"2310.16226","title":"TiC-CLIP: Continual Training of CLIP Models","created":"2023-10-24","cited_by_count":38,"area":null},{"id":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"id":"2111.06399","title":"Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification","created":"2021-11-10","cited_by_count":35,"area":null},{"id":"2308.03793","title":"ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation","created":"2023-08-04","cited_by_count":35,"area":"mllm"},{"id":"2211.00463","title":"Amplifying Membership Exposure via Data Poisoning","created":"2022-11-01","cited_by_count":34,"area":"safety"},{"id":"2401.04578","title":"Effective pruning of web-scale datasets based on complexity of concept clusters","created":"2024-01-09","cited_by_count":34,"area":null},{"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,"area":"mllm"},{"id":"2108.10048","title":"How Transferable Are Self-supervised Features in Medical Image Classification Tasks?","created":"2021-08-23","cited_by_count":33,"area":null},{"id":"2111.08687","title":"INTERN: A New Learning Paradigm Towards General Vision","created":"2021-11-16","cited_by_count":33,"area":null},{"id":"2207.12661","title":"Learning Visual Representation from Modality-Shared Contrastive Language-Image Pre-training","created":"2022-07-26","cited_by_count":32,"area":null},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32,"area":null},{"id":"2402.02382","title":"Revisiting the Power of Prompt for Visual Tuning","created":"2024-02-04","cited_by_count":32,"area":null},{"id":"2408.04810","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","created":"2024-08-09","cited_by_count":31,"area":"lr"},{"id":"2203.05126","title":"PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks","created":"2022-03-10","cited_by_count":30,"area":null},{"id":"2106.12864","title":"A Systematic Collection of Medical Image Datasets for Deep Learning","created":"2021-06-24","cited_by_count":29,"area":null},{"id":"2208.08789","title":"Towards Label-efficient Automatic Diagnosis and Analysis: A Comprehensive Survey of Advanced Deep Learning-based Weakly-supervised, Semi-supervised and Self-supervised Techniques in Histopathological Image Analysis","created":"2022-08-18","cited_by_count":29,"area":null},{"id":"2306.13384","title":"DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology","created":"2023-06-23","cited_by_count":29,"area":"diffusion"},{"id":"2310.19656","title":"Domain Generalization in Computational Pathology: Survey and Guidelines","created":"2023-10-30","cited_by_count":29,"area":null},{"id":"2402.14015","title":"Corrective Machine Unlearning","created":"2024-02-21","cited_by_count":29,"area":"safety"},{"id":"2507.07796","title":"Visual Instance-aware Prompt Tuning","created":"2025-07-10","cited_by_count":29,"area":null},{"id":"2303.18232","title":"DIME-FM: DIstilling Multimodal and Efficient Foundation Models","created":"2023-03-31","cited_by_count":28,"area":"mllm"},{"id":"2407.00203","title":"PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent Collaboration","created":"2024-06-28","cited_by_count":28,"area":"mllm"},{"id":"2206.04176","title":"VN-Transformer: Rotation-Equivariant Attention for Vector Neurons","created":"2022-06-08","cited_by_count":27,"area":null},{"id":"2306.06722","title":"$E(2)$-Equivariant Vision Transformer","created":"2023-06-11","cited_by_count":27,"area":null},{"id":"2309.17002","title":"Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks","created":"2023-09-29","cited_by_count":27,"area":null},{"id":"2203.09250","title":"Symmetry-Based Representations for Artificial and Biological General Intelligence","created":"2022-03-17","cited_by_count":26,"area":null},{"id":"2206.08671","title":"FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification","created":"2022-06-17","cited_by_count":26,"area":null},{"id":"2206.14973","title":"Benchmarking the Robustness of Deep Neural Networks to Common Corruptions in Digital Pathology","created":"2022-06-30","cited_by_count":26,"area":null},{"id":"2310.19859","title":"Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone","created":"2023-10-30","cited_by_count":26,"area":null},{"id":"2210.09304","title":"Non-Contrastive Learning Meets Language-Image Pre-Training","created":"2022-10-17","cited_by_count":25,"area":null},{"id":"2412.12153","title":"Revisiting Weight Averaging for Model Merging","created":"2024-12-11","cited_by_count":25,"area":null},{"id":"2312.06224","title":"Medical Vision Language Pretraining: A survey","created":"2023-12-11","cited_by_count":24,"area":"mllm"},{"id":"2310.06131","title":"Learning Layer-wise Equivariances Automatically using Gradients","created":"2023-10-09","cited_by_count":23,"area":null},{"id":"2402.02242","title":"Parameter-Efficient Fine-Tuning for Pre-Trained Vision Models: A Survey and Benchmark","created":"2024-02-03","cited_by_count":23,"area":null},{"id":"2404.15217","title":"Towards Large-Scale Training of Pathology Foundation Models","created":"2024-03-24","cited_by_count":23,"area":null},{"id":"2406.06973","title":"RWKV-CLIP: A Robust Vision-Language Representation Learner","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2410.21802","title":"Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models","created":"2024-10-29","cited_by_count":23,"area":"mllm"},{"id":"2105.05400","title":"Homogeneous vector bundles and $G$-equivariant convolutional neural networks","created":"2021-05-12","cited_by_count":21,"area":null},{"id":"2106.07512","title":"Last Layer Marginal Likelihood for Invariance Learning","created":"2021-06-14","cited_by_count":21,"area":null}],"next_cursor":"100"}