{"total":42,"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":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2404.08031","title":"Latent Guard: a Safety Framework for Text-to-image Generation","created":"2024-04-11","cited_by_count":71,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2405.20469","title":"Is Synthetic Data all We Need? Benchmarking the Robustness of Models Trained with Synthetic Images","created":"2024-05-30","cited_by_count":41,"area":null},{"id":"2410.16512","title":"TIPS: Text-Image Pretraining with Spatial awareness","created":"2024-10-21","cited_by_count":37,"area":null},{"id":"2410.05249","title":"LoTLIP: Improving Language-Image Pre-training for Long Text Understanding","created":"2024-10-07","cited_by_count":27,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"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":"2403.06952","title":"SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data","created":"2024-03-11","cited_by_count":14,"area":null},{"id":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2503.09436","title":"PromptMap: An Alternative Interaction Style for AI-Based Image Generation","created":"2025-03-12","cited_by_count":8,"area":null},{"id":"2403.13808","title":"On Pretraining Data Diversity for Self-Supervised Learning","created":"2024-03-20","cited_by_count":7,"area":null},{"id":"2407.06723","title":"Graph-Based Captioning: Enhancing Visual Descriptions by Interconnecting Region Captions","created":"2024-07-09","cited_by_count":7,"area":null},{"id":"2503.17080","title":"Seeing What Matters: Empowering CLIP with Patch Generation-to-Selection","created":"2025-03-21","cited_by_count":7,"area":null},{"id":"2507.10095","title":"FIX-CLIP: Dual-Branch Hierarchical Contrastive Learning via Synthetic Captions for Better Understanding of Long Text","created":"2025-07-14","cited_by_count":7,"area":null},{"id":"2512.14480","title":"SuperCLIP: CLIP with Simple Classification Supervision","created":"2025-12-16","cited_by_count":4,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2509.22635","title":"Training-Free Synthetic Data Generation with Dual IP-Adapter Guidance","created":"2025-09-26","cited_by_count":3,"area":null},{"id":"2406.09388","title":"Exploring the Spectrum of Visio-Linguistic Compositionality and Recognition","created":"2024-06-13","cited_by_count":2,"area":null},{"id":"2406.12368","title":"MixDiff: Mixing Natural and Synthetic Images for Robust Self-Supervised Representations","created":"2024-06-18","cited_by_count":2,"area":null},{"id":"2512.11141","title":"Learning complete and explainable visual representations from itemized text supervision","created":"2025-12-11","cited_by_count":2,"area":null},{"id":"2605.18608","title":"Dance Across Shifts: Forward-Facilitation Continual Test-Time Adaptation through Dynamic Style Bridging","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2407.03463","title":"Precision at Scale: Domain-Specific Datasets On-Demand","created":"2024-07-03","cited_by_count":1,"area":null},{"id":"2410.10160","title":"Will the Inclusion of Generated Data Amplify Bias Across Generations in Future Image Classification Models?","created":"2024-10-14","cited_by_count":1,"area":null},{"id":"2505.11703","title":"LoFT: LoRA-fused Training Dataset Generation with Few-shot Guidance","created":"2025-05-16","cited_by_count":1,"area":null},{"id":"2508.17497","title":"Multimodal Representation Learning Conditioned on Semantic Relations","created":"2025-08-24","cited_by_count":1,"area":null},{"id":"2512.11982","title":"Semantic search for 100M+ galaxy images using AI-generated captions","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2602.22734","title":"Asymmetric Idiosyncrasies in Multimodal Models","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2404.03256","title":"Multi Positive Contrastive Learning with Pose-Consistent Generated Images","created":"2024-04-04","cited_by_count":0,"area":null},{"id":"2409.00347","title":"Chatting Up Attachment: Using LLMs to Predict Adult Bonds","created":"2024-08-31","cited_by_count":0,"area":null},{"id":"2411.15611","title":"If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2509.11661","title":"DTGen: Generative Diffusion-Based Few-Shot Data Augmentation for Fine-Grained Dirty Tableware Recognition","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2511.01517","title":"NSYNC: Negative Synthetic Image Generation for Contrastive Training to Improve Stylized Text-To-Image Translation","created":"2025-11-03","cited_by_count":0,"area":null},{"id":"2601.21426","title":"MultiModal Fine-tuning with Synthetic Captions","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.24294","title":"VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection","created":"2026-03-25","cited_by_count":0,"area":null},{"id":"2606.08336","title":"Synesthesia via Direct Latent Augmentation:Bypassing the Decode-Encode Loop for Cross-Modal Distillation","created":"2026-06-06","cited_by_count":0,"area":null},{"id":"2607.02637","title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.22924","title":"Layering Virtual Try-On","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.00440","title":"Poplar: A Scalable Pipeline for Human-Centric Image Dataset Synthesis","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2609.35090","title":"Advancing Video-Text Pretraining with Multi-View Captions","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}