{"total":19,"rows":[{"id":"2312.12359","title":"CLIP-DINOiser: Teaching CLIP a few DINO tricks for open-vocabulary semantic segmentation","created":"2023-12-19","cited_by_count":96,"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":"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":"2406.03345","title":"Feature contamination: Neural networks learn uncorrelated features and fail to generalize","created":"2024-06-05","cited_by_count":11,"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":"2411.02837","title":"On the Comparison between Multi-modal and Single-modal Contrastive Learning","created":"2024-11-05","cited_by_count":10,"area":null},{"id":"2412.02856","title":"Is Large-Scale Pretraining the Secret to Good Domain Generalization?","created":"2024-12-03","cited_by_count":9,"area":null},{"id":"2504.13101","title":"Position: An Empirically Grounded Identifiability Theory Will Accelerate Self-Supervised Learning Research","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2410.14729","title":"Is Less More? Exploring Token Condensation as Training-free Test-time Adaptation","created":"2024-10-16","cited_by_count":4,"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":"2409.17085","title":"Parameter-efficient Bayesian Neural Networks for Uncertainty-aware Depth Estimation","created":"2024-09-25","cited_by_count":3,"area":null},{"id":"2506.16950","title":"LAION-C: An Out-of-Distribution Benchmark for Web-Scale Vision Models","created":"2025-06-20","cited_by_count":3,"area":null},{"id":"2405.17139","title":"Synergy and Diversity in CLIP: Enhancing Performance Through Adaptive Backbone Ensembling","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2603.05768","title":"Bridging Domains through Subspace-Aware Model Merging","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2508.16051","title":"MMAPG: A Training-Free Framework for Multimodal Multi-hop Question Answering via Adaptive Planning Graphs","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2503.13058","title":"Do Vision Models Develop Human-Like Progressive Difficulty Understanding?","created":"2025-03-17","cited_by_count":0,"area":null},{"id":"2506.14008","title":"FindMeIfYouCan: Bringing Open Set metrics to $\\textit{near} $, $ \\textit{far} $ and $\\textit{farther}$ Out-of-Distribution Object Detection","created":"2025-06-16","cited_by_count":0,"area":null},{"id":"2509.24420","title":"A Data-Centric Perspective on the Influence of Image Data Quality in Machine Learning Models","created":"2025-09-29","cited_by_count":0,"area":null},{"id":"2608.04442","title":"Robustness Emerges Early in Training Dynamics, but Is Not Preserved","created":"2026-08-05","cited_by_count":0,"area":null}],"next_cursor":null}