{"total":114,"rows":[{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111,"area":null},{"id":"2312.04567","title":"Scaling Laws of Synthetic Images for Model Training ... for Now","created":"2023-12-07","cited_by_count":108,"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":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"area":null},{"id":"2307.15208","title":"Generative AI for Medical Imaging: extending the MONAI Framework","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2402.01832","title":"SynthCLIP: Are We Ready for a Fully Synthetic CLIP Training?","created":"2024-02-02","cited_by_count":64,"area":null},{"id":"2502.20056","title":"Enhanced Contrastive Learning with Multi-view Longitudinal Data for Chest X-ray Report Generation","created":"2025-02-27","cited_by_count":42,"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":"2310.10402","title":"Real-Fake: Effective Training Data Synthesis Through Distribution Matching","created":"2023-10-16","cited_by_count":36,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2411.02372","title":"Learning General-Purpose Biomedical Volume Representations using Randomized Synthesis","created":"2024-11-04","cited_by_count":29,"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":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2412.08467","title":"Bootstrapping Language-Guided Navigation Learning with Self-Refining Data Flywheel","created":"2024-12-11","cited_by_count":20,"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":"2312.03631","title":"Mitigating Open-Vocabulary Caption Hallucinations","created":"2023-12-06","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":"2502.15588","title":"Improving the Scaling Laws of Synthetic Data with Deliberate Practice","created":"2025-02-21","cited_by_count":17,"area":null},{"id":"2503.19480","title":"GenHancer: Imperfect Generative Models are Secretly Strong Vision-Centric Enhancers","created":"2025-03-25","cited_by_count":16,"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":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2503.23398","title":"A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models","created":"2025-03-30","cited_by_count":14,"area":null},{"id":"2310.01830","title":"AI-Generated Images as Data Source: The Dawn of Synthetic Era","created":"2023-10-03","cited_by_count":13,"area":null},{"id":"2411.11927","title":"FLAME: Frozen Large Language Models Enable Data-Efficient Language-Image Pre-training","created":"2024-11-18","cited_by_count":12,"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":"2312.03046","title":"Diversified in-domain synthesis with efficient fine-tuning for few-shot classification","created":"2023-12-05","cited_by_count":11,"area":null},{"id":"2503.15485","title":"TULIP: Towards Unified Language-Image Pretraining","created":"2025-03-19","cited_by_count":11,"area":null},{"id":"2403.03194","title":"MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets","created":"2024-03-05","cited_by_count":10,"area":null},{"id":"2403.12003","title":"GenView: Enhancing View Quality with Pretrained Generative Model for Self-Supervised Learning","created":"2024-03-18","cited_by_count":9,"area":null},{"id":"2407.18134","title":"$\\mathbb{X}$-Sample Contrastive Loss: Improving Contrastive Learning with Sample Similarity Graphs","created":"2024-07-25","cited_by_count":9,"area":null},{"id":"2410.04345","title":"MVP-Bench: Can Large Vision--Language Models Conduct Multi-level Visual Perception Like Humans?","created":"2024-10-06","cited_by_count":9,"area":null},{"id":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2312.05272","title":"GenQ: Quantization in Low Data Regimes with Generative Synthetic Data","created":"2023-12-07","cited_by_count":8,"area":null},{"id":"2410.00201","title":"DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation","created":"2024-09-30","cited_by_count":8,"area":null},{"id":"2509.16664","title":"$\\boldsymbol{\\lambda}$-Orthogonality Regularization for Compatible Representation Learning","created":"2025-09-20","cited_by_count":8,"area":null},{"id":"2310.01330","title":"Towards reporting bias in visual-language datasets: bimodal augmentation by decoupling object-attribute association","created":"2023-10-02","cited_by_count":7,"area":null},{"id":"2403.19866","title":"Is Synthetic Image Useful for Transfer Learning? An Investigation into Data Generation, Volume, and Utilization","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2510.19557","title":"The Intricate Dance of Prompt Complexity, Quality, Diversity, and Consistency in T2I Models","created":"2025-10-22","cited_by_count":6,"area":null},{"id":"2510.21605","title":"S3OD: Towards Generalizable Salient Object Detection with Synthetic Data","created":"2025-10-24","cited_by_count":6,"area":null},{"id":"2404.17063","title":"WheelPose: Data Synthesis Techniques to Improve Pose Estimation Performance on Wheelchair Users","created":"2024-04-25","cited_by_count":5,"area":null},{"id":"2312.14369","title":"Quality-Diversity Generative Sampling for Learning with Synthetic Data","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2403.18334","title":"DODA: Adapting Object Detectors to Dynamic Agricultural Environments in Real-Time with Diffusion","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2404.03200","title":"Future-Proofing Class-Incremental Learning","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2405.13779","title":"Robust Disaster Assessment from Aerial Imagery Using Text-to-Image Synthetic Data","created":"2024-05-22","cited_by_count":4,"area":null},{"id":"2406.11988","title":"Decomposed evaluations of geographic disparities in text-to-image models","created":"2024-06-17","cited_by_count":4,"area":null},{"id":"2410.14602","title":"Data Diversity as Implicit Regularization: How Does Diversity Shape the Weight Space of Deep Neural Networks?","created":"2024-10-18","cited_by_count":4,"area":null},{"id":"2411.10224","title":"EVOKE: Elevating Chest X-ray Report Generation via Multi-View Contrastive Learning and Patient-Specific Knowledge","created":"2024-11-15","cited_by_count":4,"area":null},{"id":"2501.01760","title":"From Age Estimation to Age-Invariant Face Recognition: Generalized Age Feature Extraction Using Order-Enhanced Contrastive Learning","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2403.05966","title":"Can Generative Models Improve Self-Supervised Representation Learning?","created":"2024-03-09","cited_by_count":3,"area":null},{"id":"2407.15296","title":"Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection","created":"2024-07-21","cited_by_count":3,"area":null},{"id":"2410.21153","title":"Synthetica: Large Scale Synthetic Data for Robot Perception","created":"2024-10-28","cited_by_count":3,"area":null},{"id":"2502.15901","title":"TS-OOD: Evaluating Time-Series Out-of-Distribution Detection and Prospective Directions for Progress","created":"2025-02-21","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":"2602.02334","title":"VQ-Style: Disentangling Style and Content in Motion with Residual Quantized Representations","created":"2026-02-02","cited_by_count":3,"area":null},{"id":"2401.00420","title":"SynCDR : Training Cross Domain Retrieval Models with Synthetic Data","created":"2023-12-31","cited_by_count":2,"area":null},{"id":"2405.16016","title":"ComFace: Facial Representation Learning with Synthetic Data for Comparing Faces","created":"2024-05-25","cited_by_count":2,"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":"2410.01816","title":"Automatic Scene Generation: State-of-the-Art Techniques, Models, Datasets, Challenges, and Future Prospects","created":"2024-09-14","cited_by_count":2,"area":null},{"id":"2412.09115","title":"Vision CNNs trained to estimate spatial latents learned similar ventral-stream-aligned representations","created":"2024-12-12","cited_by_count":2,"area":null},{"id":"2503.00296","title":"Synthetic data enables context-aware bioacoustic sound event detection","created":"2025-03-01","cited_by_count":2,"area":null},{"id":"2505.06948","title":"Unsupervised Learning for Class Distribution Mismatch","created":"2025-05-11","cited_by_count":2,"area":null},{"id":"2505.19495","title":"The Role of Video Generation in Enhancing Data-Limited Action Understanding","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2505.20655","title":"Photography Perspective Composition: Towards Aesthetic Perspective Recommendation","created":"2025-05-27","cited_by_count":2,"area":null},{"id":"2603.04803","title":"Guiding Diffusion-based Reconstruction with Contrastive Signals for Balanced Visual Representation","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.14505","title":"Unlocking the Latent Canvas: Eliciting and Benchmarking Symbolic Visual Expression in LLMs","created":"2026-03-15","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":"2307.08526","title":"Image Captions are Natural Prompts for Text-to-Image Models","created":"2023-07-17","cited_by_count":1,"area":null},{"id":"2310.19653","title":"A Note on Generalization in Variational Autoencoders: How Effective Is Synthetic Data & Overparameterization?","created":"2023-10-30","cited_by_count":1,"area":null},{"id":"2406.05923","title":"Contrastive Learning from Synthetic Audio Doppelg\\\"angers","created":"2024-06-09","cited_by_count":1,"area":null},{"id":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2412.17346","title":"FFA Sora, video generation as fundus fluorescein angiography simulator","created":"2024-12-23","cited_by_count":1,"area":null},{"id":"2501.05130","title":"Contrastive Representation Modeling for Anomaly Detection","created":"2025-01-09","cited_by_count":1,"area":null},{"id":"2503.18507","title":"Can Text-to-Video Generation help Video-Language Alignment?","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2503.22171","title":"An Empirical Study of Validating Synthetic Data for Text-Based Person Retrieval","created":"2025-03-28","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":"2505.16972","title":"From Tens of Hours to Tens of Thousands: Scaling Back-Translation for Speech Recognition","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2507.02493","title":"Temporally-Aware Supervised Contrastive Learning for Polyp Counting in Colonoscopy","created":"2025-07-03","cited_by_count":1,"area":null},{"id":"2510.09171","title":"Instance-Level Generation for Representation Learning","created":"2025-10-10","cited_by_count":1,"area":null},{"id":"2511.14901","title":"FarSLIP: Discovering Effective CLIP Adaptation for Fine-Grained Remote Sensing Understanding","created":"2025-11-18","cited_by_count":1,"area":null},{"id":"2512.08854","title":"Is Generation Required for Data-Efficient Perception?","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2603.02667","title":"Unifying Contrastive and Generative Objectives for Visual Understanding and Text-to-Image Generation","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.26353","title":"Personalized Generative Models for Contextual Debiasing","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2403.01306","title":"ICC: Quantifying Image Caption Concreteness for Multimodal Dataset Curation","created":"2024-03-02","cited_by_count":0,"area":null},{"id":"2403.18132","title":"Recommendation of data-free class-incremental learning algorithms by simulating future data","created":"2024-03-26","cited_by_count":0,"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":"2404.12958","title":"Improving Pediatric Pneumonia Diagnosis with Adult Chest X-ray Images Utilizing Contrastive Learning and Embedding Similarity","created":"2024-04-19","cited_by_count":0,"area":null},{"id":"2406.13735","title":"StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic Images","created":"2024-06-19","cited_by_count":0,"area":null},{"id":"2409.08884","title":"Detect Fake with Fake: Leveraging Synthetic Data-driven Representation for Synthetic Image Detection","created":"2024-09-13","cited_by_count":0,"area":null},{"id":"2409.17685","title":"FICAug: Feature-Informed Clustering and Augmentation for Facial-Expression-Based Parkinson's Disease Screening","created":"2024-09-26","cited_by_count":0,"area":null},{"id":"2410.01697","title":"Enhancing Adversarial Robustness through Multi-Objective Representation Learning","created":"2024-10-02","cited_by_count":0,"area":null},{"id":"2412.18460","title":"GeFL: Model-Agnostic Federated Learning with Generative Models","created":"2024-12-24","cited_by_count":0,"area":null},{"id":"2501.09278","title":"Text-guided Synthetic Geometric Augmentation for Zero-shot 3D Understanding","created":"2025-01-16","cited_by_count":0,"area":null},{"id":"2501.13718","title":"A Mutual Information Perspective on Multiple Latent Variable Generative Models for Positive View Generation","created":"2025-01-23","cited_by_count":0,"area":null},{"id":"2503.04687","title":"Compositional World Knowledge leads to High Utility Synthetic data","created":"2025-03-06","cited_by_count":0,"area":null},{"id":"2505.02304","title":"Generative Sign-description Prompts with Multi-positive Contrastive Learning for Sign Language Recognition","created":"2025-05-05","cited_by_count":0,"area":null},{"id":"2505.13099","title":"Industrial Synthetic Segment Pre-training","created":"2025-05-19","cited_by_count":0,"area":null},{"id":"2506.13496","title":"Hierarchical Multi-Positive Contrastive Learning for Patent Image Retrieval","created":"2025-06-16","cited_by_count":0,"area":null}],"next_cursor":"100"}