{"total":97,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"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":"2309.17425","title":"Data Filtering Networks","created":"2023-09-29","cited_by_count":250,"area":null},{"id":"2211.04325","title":"Will we run out of data? Limits of LLM scaling based on human-generated data","created":"2022-10-26","cited_by_count":195,"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":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","cited_by_count":119,"area":"mllm"},{"id":"2212.10445","title":"Model Ratatouille: Recycling Diverse Models for Out-of-Distribution Generalization","created":"2022-12-20","cited_by_count":97,"area":null},{"id":"2307.10350","title":"Improving Multimodal Datasets with Image Captioning","created":"2023-07-19","cited_by_count":93,"area":"mllm"},{"id":"2302.02503","title":"Leaving Reality to Imagination: Robust Classification via Generated Datasets","created":"2023-02-05","cited_by_count":91,"area":null},{"id":"2212.04825","title":"A Whac-A-Mole Dilemma: Shortcuts Come in Multiples Where Mitigating One Amplifies Others","created":"2022-12-09","cited_by_count":85,"area":null},{"id":"2406.18915","title":"Manipulate-Anything: Automating Real-World Robots using Vision-Language Models","created":"2024-06-27","cited_by_count":83,"area":"mllm"},{"id":"2304.08442","title":"The MiniPile Challenge for Data-Efficient Language Models","created":"2023-04-17","cited_by_count":75,"area":null},{"id":"2404.04125","title":"No \"Zero-Shot\" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance","created":"2024-04-04","cited_by_count":75,"area":null},{"id":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2403.08632","title":"A Decade's Battle on Dataset Bias: Are We There Yet?","created":"2024-03-13","cited_by_count":47,"area":null},{"id":"2404.01260","title":"Bridging Remote Sensors with Multisensor Geospatial Foundation Models","created":"2024-04-01","cited_by_count":46,"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":"2405.17426","title":"Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving","created":"2024-05-27","cited_by_count":41,"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":"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":"2411.00997","title":"Identifying Implicit Social Biases in Vision-Language Models","created":"2024-11-01","cited_by_count":27,"area":"mllm"},{"id":"2307.12532","title":"On the Connection between Pre-training Data Diversity and Fine-tuning Robustness","created":"2023-07-24","cited_by_count":25,"area":null},{"id":"2403.02677","title":"Finetuned Multimodal Language Models Are High-Quality Image-Text Data Filters","created":"2024-03-05","cited_by_count":25,"area":"mllm"},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2404.08958","title":"AMU-Tuning: Effective Logit Bias for CLIP-based Few-shot Learning","created":"2024-04-13","cited_by_count":22,"area":"mllm"},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2407.09033","title":"Textual Query-Driven Mask Transformer for Domain Generalized Segmentation","created":"2024-07-12","cited_by_count":21,"area":"mllm"},{"id":"2402.07417","title":"An Empirical Study Into What Matters for Calibrating Vision-Language Models","created":"2024-02-12","cited_by_count":20,"area":"mllm"},{"id":"2405.19547","title":"CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning","created":"2024-05-29","cited_by_count":20,"area":"mllm"},{"id":"2309.15954","title":"The Devil is in the Details: A Deep Dive into the Rabbit Hole of Data Filtering","created":"2023-09-27","cited_by_count":19,"area":null},{"id":"2406.05184","title":"The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better","created":"2024-06-07","cited_by_count":19,"area":null},{"id":"2411.18674","title":"Active Data Curation Effectively Distills Large-Scale Multimodal Models","created":"2024-11-27","cited_by_count":19,"area":"distill"},{"id":"2302.13602","title":"The Role of Pre-training Data in Transfer Learning","created":"2023-02-27","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":"2506.16895","title":"With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You","created":"2025-06-20","cited_by_count":16,"area":null},{"id":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2405.08209","title":"Who's in and who's out? A case study of multimodal CLIP-filtering in DataComp","created":"2024-05-13","cited_by_count":15,"area":null},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2408.04154","title":"The Data Addition Dilemma","created":"2024-08-08","cited_by_count":15,"area":null},{"id":"2501.11175","title":"ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models","created":"2025-01-19","cited_by_count":15,"area":"mllm"},{"id":"2209.13435","title":"Scaling Laws For Deep Learning Based Image Reconstruction","created":"2022-09-27","cited_by_count":14,"area":null},{"id":"2405.16915","title":"Multilingual Diversity Improves Vision-Language Representations","created":"2024-05-27","cited_by_count":14,"area":null},{"id":"2302.01381","title":"Effective Robustness against Natural Distribution Shifts for Models with Different Training Data","created":"2023-02-02","cited_by_count":13,"area":null},{"id":"2302.12480","title":"Robust Weight Signatures: Gaining Robustness as Easy as Patching Weights?","created":"2023-02-24","cited_by_count":13,"area":null},{"id":"2307.13136","title":"Does Progress On Object Recognition Benchmarks Improve Real-World Generalization?","created":"2023-07-24","cited_by_count":13,"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":"2407.05897","title":"Deciphering the Role of Representation Disentanglement: Investigating Compositional Generalization in CLIP Models","created":"2024-07-08","cited_by_count":13,"area":null},{"id":"2410.01534","title":"Toward a Holistic Evaluation of Robustness in CLIP Models","created":"2024-10-02","cited_by_count":13,"area":"mllm"},{"id":"2411.07854","title":"Tucano: Advancing Neural Text Generation for Portuguese","created":"2024-11-12","cited_by_count":13,"area":null},{"id":"2312.10271","title":"Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2306.15769","title":"What Makes ImageNet Look Unlike LAION","created":"2023-06-27","cited_by_count":9,"area":null},{"id":"2307.10586","title":"A Holistic Assessment of the Reliability of Machine Learning Systems","created":"2023-07-20","cited_by_count":9,"area":null},{"id":"2310.08577","title":"Visual Data-Type Understanding does not emerge from Scaling Vision-Language Models","created":"2023-10-12","cited_by_count":9,"area":"mllm"},{"id":"2311.09006","title":"Data Similarity is Not Enough to Explain Language Model Performance","created":"2023-11-15","cited_by_count":9,"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":"2412.14056","title":"A Review of Multimodal Explainable Artificial Intelligence: Past, Present and Future","created":"2024-12-18","cited_by_count":9,"area":null},{"id":"2502.09507","title":"When and How Does CLIP Enable Domain and Compositional Generalization?","created":"2025-02-13","cited_by_count":9,"area":"mllm"},{"id":"2403.06869","title":"Impact of Noisy Supervision in Foundation Model Learning","created":"2024-03-11","cited_by_count":8,"area":null},{"id":"2407.11855","title":"Scaling Sign Language Translation","created":"2024-07-16","cited_by_count":8,"area":null},{"id":"2411.11667","title":"Dissecting Representation Misalignment in Contrastive Learning via Influence Function","created":"2024-11-18","cited_by_count":8,"area":null},{"id":"2503.14377","title":"Advancing Medical Representation Learning Through High-Quality Data","created":"2025-03-18","cited_by_count":8,"area":null},{"id":"2303.14333","title":"Train/Test-Time Adaptation with Retrieval","created":"2023-03-25","cited_by_count":7,"area":null},{"id":"2304.08479","title":"Towards Robust Prompts on Vision-Language Models","created":"2023-04-17","cited_by_count":7,"area":"mllm"},{"id":"2405.10286","title":"FFF: Fixing Flawed Foundations in contrastive pre-training results in very strong Vision-Language models","created":"2024-05-16","cited_by_count":7,"area":"mllm"},{"id":"2504.06962","title":"Efficient Self-Supervised Learning for Earth Observation via Dynamic Dataset Curation","created":"2025-04-09","cited_by_count":7,"area":null},{"id":"2310.13040","title":"Interpreting CLIP: Insights on the Robustness to ImageNet Distribution Shifts","created":"2023-10-19","cited_by_count":6,"area":null},{"id":"2407.18941","title":"LEMoN: Label Error Detection using Multimodal Neighbors","created":"2024-07-10","cited_by_count":6,"area":"mllm"},{"id":"2307.05610","title":"Substance or Style: What Does Your Image Embedding Know?","created":"2023-07-10","cited_by_count":5,"area":null},{"id":"2407.11121","title":"Towards Adversarially Robust Vision-Language Models: Insights from Design Choices and Prompt Formatting Techniques","created":"2024-07-15","cited_by_count":5,"area":"mllm"},{"id":"2410.05057","title":"SELECT: A Large-Scale Benchmark of Data Curation Strategies for Image Classification","created":"2024-10-07","cited_by_count":5,"area":null},{"id":"2412.19920","title":"Not all Views are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation Models","created":"2024-12-27","cited_by_count":5,"area":null},{"id":"2501.12535","title":"How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models?","created":"2025-01-21","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":"2310.07632","title":"Prompt Backdoors in Visual Prompt Learning","created":"2023-10-11","cited_by_count":4,"area":"safety"},{"id":"2502.07732","title":"When Incentives Backfire, Data Stops Being Human","created":"2025-02-11","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":"2305.12811","title":"Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher Quality","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2308.03821","title":"Distributionally Robust Classification on a Data Budget","created":"2023-08-07","cited_by_count":2,"area":null},{"id":"2310.00783","title":"Propagating Semantic Labels in Video Data","created":"2023-10-01","cited_by_count":2,"area":null},{"id":"2406.14473","title":"Data-Centric AI in the Age of Large Language Models","created":"2024-06-20","cited_by_count":2,"area":null},{"id":"2506.08194","title":"GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra","created":"2025-06-09","cited_by_count":2,"area":"lr"},{"id":"2510.14376","title":"DOS: Directional Object Separation in Text Embeddings for Multi-Object Image Generation","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2311.04016","title":"Exploring Dataset-Scale Indicators of Data Quality","created":"2023-11-07","cited_by_count":1,"area":null},{"id":"2403.07888","title":"Cross-modality debiasing: using language to mitigate sub-population shifts in imaging","created":"2024-02-02","cited_by_count":1,"area":null},{"id":"2502.14583","title":"A Theory for Conditional Generative Modeling on Multiple Data Sources","created":"2025-02-20","cited_by_count":1,"area":null},{"id":"2505.11771","title":"Residual Feature Integration is Sufficient to Prevent Negative Transfer","created":"2025-05-17","cited_by_count":1,"area":null},{"id":"2506.09846","title":"Learning to Align: Addressing Character Frequency Distribution Shifts in Handwritten Text Recognition","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2509.12358","title":"Unsupervised Atomic Data Mining via Multi-Kernel Graph Autoencoders for Machine Learning Force Fields","created":"2025-09-15","cited_by_count":1,"area":null},{"id":"2305.08017","title":"How to Train Your CheXDragon: Training Chest X-Ray Models for Transfer to Novel Tasks and Healthcare Systems","created":"2023-05-13","cited_by_count":0,"area":null},{"id":"2311.17949","title":"Zero-shot Retrieval: Augmenting Pre-trained Models with Search Engines","created":"2023-11-29","cited_by_count":0,"area":null},{"id":"2409.12076","title":"Unsupervised Domain Adaptation Via Data Pruning","created":"2024-09-18","cited_by_count":0,"area":null},{"id":"2505.11895","title":"Adversarial Robustness for Unified Multi-Modal Encoders via Efficient Calibration","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2511.05057","title":"Role-SynthCLIP: A Role Play Driven Diverse Synthetic Data Approach","created":"2025-11-07","cited_by_count":0,"area":"synth"},{"id":"2512.14230","title":"Understanding the Gain from Data Filtering in Multimodal Contrastive Learning","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2606.23611","title":"Data Selection Through Iterative Self-Filtering for Vision-Language Settings","created":"2026-06-22","cited_by_count":0,"area":null}],"next_cursor":null}