{"total":20,"rows":[{"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":"2311.09215","title":"ConvNet vs Transformer, Supervised vs CLIP: Beyond ImageNet Accuracy","created":"2023-11-15","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":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2405.15018","title":"What Variables Affect Out-of-Distribution Generalization in Pretrained Models?","created":"2024-05-23","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":"2502.10691","title":"Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning","created":"2025-02-15","cited_by_count":11,"area":null},{"id":"2403.04484","title":"Source Matters: Source Dataset Impact on Model Robustness in Medical Imaging","created":"2024-03-07","cited_by_count":10,"area":null},{"id":"2310.14356","title":"Semantic and Expressive Variation in Image Captions Across Languages","created":"2023-10-22","cited_by_count":8,"area":null},{"id":"2403.00194","title":"Ask Your Distribution Shift if Pre-Training is Right for You","created":"2024-02-29","cited_by_count":7,"area":null},{"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":"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":"2506.11111","title":"Evaluating and Improving Robustness in Large Language Models: A Survey and Future Directions","created":"2025-06-08","cited_by_count":5,"area":null},{"id":"2410.03140","title":"In-context Learning in Presence of Spurious Correlations","created":"2024-10-04","cited_by_count":3,"area":null},{"id":"2511.00256","title":"NaturalVoices: A Large-Scale, Spontaneous and Emotional Podcast Dataset for Voice Conversion","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2403.19822","title":"Multi-Stage Multi-Modal Pre-Training for Automatic Speech Recognition","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2406.05628","title":"Domain Generalization Guided by Large-Scale Pre-Trained Priors","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2505.19893","title":"ESLM: Risk-Averse Selective Language Modeling for Efficient Pretraining","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2604.21104","title":"Pretrain Where? Investigating How Pretraining Data Diversity Impacts Geospatial Foundation Model Performance","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2501.08506","title":"Exploring the Efficacy of Meta-Learning: Unveiling Superior Data Diversity Utilization of MAML Over Pre-training","created":"2025-01-15","cited_by_count":0,"area":null}],"next_cursor":null}