{"total":119,"rows":[{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152,"area":null},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109,"area":null},{"id":"2203.05482","title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","created":"2022-03-10","cited_by_count":1396,"area":null},{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120,"area":null},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766,"area":null},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694,"area":null},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691,"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":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2212.00794","title":"Scaling Language-Image Pre-training via Masking","created":"2022-12-01","cited_by_count":317,"area":null},{"id":"2205.06230","title":"Simple Open-Vocabulary Object Detection with Vision Transformers","created":"2022-05-12","cited_by_count":305,"area":null},{"id":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194,"area":null},{"id":"2208.05592","title":"Patching open-vocabulary models by interpolating weights","created":"2022-08-10","cited_by_count":190,"area":null},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178,"area":null},{"id":"2311.18803","title":"BioCLIP: A Vision Foundation Model for the Tree of Life","created":"2023-11-30","cited_by_count":161,"area":null},{"id":"2209.15639","title":"F-VLM: Open-Vocabulary Object Detection upon Frozen Vision and Language Models","created":"2022-09-30","cited_by_count":150,"area":null},{"id":"2204.10965","title":"CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks","created":"2022-04-23","cited_by_count":147,"area":null},{"id":"2205.01397","title":"Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)","created":"2022-05-03","cited_by_count":138,"area":null},{"id":"2203.10789","title":"Domain Generalization by Mutual-Information Regularization with Pre-trained Models","created":"2022-03-21","cited_by_count":133,"area":null},{"id":"2205.14459","title":"CyCLIP: Cyclic Contrastive Language-Image Pretraining","created":"2022-05-28","cited_by_count":127,"area":null},{"id":"2206.07045","title":"ReCo: Retrieve and Co-segment for Zero-shot Transfer","created":"2022-06-14","cited_by_count":117,"area":null},{"id":"2207.07411","title":"Plex: Towards Reliability using Pretrained Large Model Extensions","created":"2022-07-15","cited_by_count":102,"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":"2302.00864","title":"CLIPood: Generalizing CLIP to Out-of-Distributions","created":"2023-02-02","cited_by_count":96,"area":null},{"id":"2305.07011","title":"Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers","created":"2023-05-11","cited_by_count":91,"area":null},{"id":"2305.13035","title":"Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design","created":"2023-05-22","cited_by_count":89,"area":null},{"id":"2212.06470","title":"Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining","created":"2022-12-13","cited_by_count":88,"area":null},{"id":"2205.04596","title":"When does dough become a bagel? Analyzing the remaining mistakes on ImageNet","created":"2022-05-09","cited_by_count":61,"area":null},{"id":"2312.05208","title":"ControlRoom3D: Room Generation using Semantic Proxy Rooms","created":"2023-12-08","cited_by_count":56,"area":null},{"id":"2402.07410","title":"A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)","created":"2024-02-12","cited_by_count":44,"area":null},{"id":"2307.03132","title":"T-MARS: Improving Visual Representations by Circumventing Text Feature Learning","created":"2023-07-06","cited_by_count":43,"area":null},{"id":"2302.06235","title":"A Simple Zero-shot Prompt Weighting Technique to Improve Prompt Ensembling in Text-Image Models","created":"2023-02-13","cited_by_count":39,"area":null},{"id":"2203.05796","title":"Democratizing Contrastive Language-Image Pre-training: A CLIP Benchmark of Data, Model, and Supervision","created":"2022-03-11","cited_by_count":36,"area":null},{"id":"2301.04644","title":"Does progress on ImageNet transfer to real-world datasets?","created":"2023-01-11","cited_by_count":35,"area":null},{"id":"2310.09562","title":"Does CLIP's Generalization Performance Mainly Stem from High Train-Test Similarity?","created":"2023-10-14","cited_by_count":35,"area":null},{"id":"2408.07362","title":"BadMerging: Backdoor Attacks Against Model Merging","created":"2024-08-14","cited_by_count":34,"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":"2310.01875","title":"Towards Stable Backdoor Purification through Feature Shift Tuning","created":"2023-10-03","cited_by_count":32,"area":null},{"id":"2310.08106","title":"Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models","created":"2023-10-12","cited_by_count":32,"area":null},{"id":"2309.00775","title":"Contrastive Feature Masking Open-Vocabulary Vision Transformer","created":"2023-09-02","cited_by_count":31,"area":null},{"id":"2311.15206","title":"Insect-Foundation: A Foundation Model and Large-scale 1M Dataset for Visual Insect Understanding","created":"2023-11-26","cited_by_count":29,"area":null},{"id":"2403.18684","title":"Scaling Laws For Dense Retrieval","created":"2024-03-27","cited_by_count":29,"area":null},{"id":"2209.10304","title":"I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification","created":"2022-09-21","cited_by_count":27,"area":null},{"id":"2205.07139","title":"Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training","created":"2022-05-14","cited_by_count":26,"area":null},{"id":"2310.00927","title":"Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP","created":"2023-10-02","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":"2204.10496","title":"Multimodal Adaptive Distillation for Leveraging Unimodal Encoders for Vision-Language Tasks","created":"2022-04-22","cited_by_count":23,"area":null},{"id":"2210.12517","title":"Exploring The Landscape of Distributional Robustness for Question Answering Models","created":"2022-10-22","cited_by_count":23,"area":null},{"id":"2312.02219","title":"Behind the Magic, MERLIM: Multi-modal Evaluation Benchmark for Large Image-Language Models","created":"2023-12-03","cited_by_count":23,"area":null},{"id":"2402.02968","title":"Delving into Multi-modal Multi-task Foundation Models for Road Scene Understanding: From Learning Paradigm Perspectives","created":"2024-02-05","cited_by_count":23,"area":null},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2305.05095","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","created":"2023-05-08","cited_by_count":19,"area":null},{"id":"2302.13602","title":"The Role of Pre-training Data in Transfer Learning","created":"2023-02-27","cited_by_count":17,"area":null},{"id":"2312.14232","title":"Parrot Captions Teach CLIP to Spot Text","created":"2023-12-21","cited_by_count":17,"area":null},{"id":"2404.17507","title":"HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts","created":"2024-04-26","cited_by_count":17,"area":null},{"id":"2304.06028","title":"RECLIP: Resource-efficient CLIP by Training with Small Images","created":"2023-04-12","cited_by_count":16,"area":null},{"id":"2311.09191","title":"Domain Aligned CLIP for Few-shot Classification","created":"2023-11-15","cited_by_count":16,"area":null},{"id":"2304.10127","title":"Learning Sample Difficulty from Pre-trained Models for Reliable Prediction","created":"2023-04-20","cited_by_count":15,"area":null},{"id":"2305.00109","title":"Zero-shot performance of the Segment Anything Model (SAM) in 2D medical imaging: A comprehensive evaluation and practical guidelines","created":"2023-04-28","cited_by_count":15,"area":null},{"id":"2405.16915","title":"Multilingual Diversity Improves Vision-Language Representations","created":"2024-05-27","cited_by_count":14,"area":null},{"id":"2405.21070","title":"What Makes CLIP More Robust to Long-Tailed Pre-Training Data? A Controlled Study for Transferable Insights","created":"2024-05-31","cited_by_count":13,"area":null},{"id":"2203.14463","title":"Large-scale Bilingual Language-Image Contrastive Learning","created":"2022-03-28","cited_by_count":12,"area":null},{"id":"2407.03036","title":"SAFT: Towards Out-of-Distribution Generalization in Fine-Tuning","created":"2024-07-03","cited_by_count":12,"area":null},{"id":"2306.08658","title":"Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language Representations","created":"2023-06-14","cited_by_count":11,"area":null},{"id":"2207.00208","title":"e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce","created":"2022-07-01","cited_by_count":10,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2505.10547","title":"Real-Time Out-of-Distribution Failure Prevention via Multi-Modal Reasoning","created":"2025-05-15","cited_by_count":10,"area":null},{"id":"2404.08197","title":"Scaling (Down) CLIP: A Comprehensive Analysis of Data, Architecture, and Training Strategies","created":"2024-04-12","cited_by_count":9,"area":null},{"id":"2307.05906","title":"Mini-Batch Optimization of Contrastive Loss","created":"2023-07-12","cited_by_count":8,"area":null},{"id":"2206.05093","title":"Federated Momentum Contrastive Clustering","created":"2022-06-10","cited_by_count":7,"area":null},{"id":"2301.07836","title":"Masked Autoencoding Does Not Help Natural Language Supervision at Scale","created":"2023-01-19","cited_by_count":7,"area":null},{"id":"2306.07952","title":"MOFI: Learning Image Representations from Noisy Entity Annotated Images","created":"2023-06-13","cited_by_count":7,"area":null},{"id":"2502.09906","title":"Insect-Foundation: A Foundation Model and Large Multimodal Dataset for Vision-Language Insect Understanding","created":"2025-02-14","cited_by_count":7,"area":null},{"id":"2212.10596","title":"Open-Vocabulary Temporal Action Detection with Off-the-Shelf Image-Text Features","created":"2022-12-20","cited_by_count":6,"area":null},{"id":"2206.03139","title":"Intra-agent speech permits zero-shot task acquisition","created":"2022-06-07","cited_by_count":5,"area":null},{"id":"2312.15551","title":"On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift","created":"2023-12-24","cited_by_count":5,"area":null},{"id":"2210.07396","title":"Caption supervision enables robust learners","created":"2022-10-13","cited_by_count":4,"area":null},{"id":"2211.07122","title":"ContextCLIP: Contextual Alignment of Image-Text pairs on CLIP visual representations","created":"2022-11-14","cited_by_count":4,"area":null},{"id":"2310.04971","title":"Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift","created":"2023-10-08","cited_by_count":4,"area":null},{"id":"2403.05535","title":"Tell, Don't Show!: Language Guidance Eases Transfer Across Domains in Images and Videos","created":"2024-03-08","cited_by_count":4,"area":null},{"id":"2211.09859","title":"Data-Centric Debugging: mitigating model failures via targeted data collection","created":"2022-11-17","cited_by_count":3,"area":null},{"id":"2312.00236","title":"Brainformer: Mimic Human Visual Brain Functions to Machine Vision Models via fMRI","created":"2023-11-30","cited_by_count":3,"area":null},{"id":"2409.12499","title":"End-to-end Open-vocabulary Video Visual Relationship Detection using Multi-modal Prompting","created":"2024-09-19","cited_by_count":3,"area":null},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2202.10784","title":"RuCLIP -- new models and experiments: a technical report","created":"2022-02-22","cited_by_count":2,"area":null},{"id":"2206.07565","title":"A Meta-Analysis of Distributionally-Robust Models","created":"2022-06-15","cited_by_count":2,"area":null},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2404.19542","title":"One-Stage Open-Vocabulary Temporal Action Detection Leveraging Temporal Multi-scale and Action Label Features","created":"2024-04-30","cited_by_count":2,"area":null},{"id":"2409.01690","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2409.17777","title":"Harnessing Shared Relations via Multimodal Mixup Contrastive Learning for Multimodal Classification","created":"2024-09-26","cited_by_count":2,"area":null},{"id":"2411.19757","title":"Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models","created":"2024-11-29","cited_by_count":2,"area":null},{"id":"2501.16481","title":"Generating customized prompts for Zero-Shot Rare Event Medical Image Classification using LLM","created":"2025-01-27","cited_by_count":2,"area":null},{"id":"2503.19801","title":"SeLIP: Similarity Enhanced Contrastive Language Image Pretraining for Multi-modal Head MRI","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2505.11216","title":"GeoMM: On Geodesic Perspective for Multi-modal Learning","created":"2025-05-16","cited_by_count":2,"area":null},{"id":"2506.09781","title":"On the Similarities of Embeddings in Contrastive Learning","created":"2025-06-11","cited_by_count":2,"area":null}],"next_cursor":"100"}