{"total":177,"rows":[{"id":"2307.00716","title":"JourneyDB: A Benchmark for Generative Image Understanding","created":"2023-07-03","cited_by_count":205,"area":"mllm"},{"id":"2403.09572","title":"Eyes Closed, Safety On: Protecting Multimodal LLMs via Image-to-Text Transformation","created":"2024-03-14","cited_by_count":124,"area":"lr"},{"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":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"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":"2312.05390","title":"NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models","created":"2023-12-08","cited_by_count":47,"area":"diffusion"},{"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":"2407.20171","title":"Diffusion Feedback Helps CLIP See Better","created":"2024-07-29","cited_by_count":38,"area":"diffusion"},{"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":"2406.10429","title":"Consistency-diversity-realism Pareto fronts of conditional image generative models","created":"2024-06-14","cited_by_count":36,"area":"wm"},{"id":"2310.10477","title":"Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis","created":"2023-10-16","cited_by_count":35,"area":"alignment"},{"id":"2403.19600","title":"Enhance Image Classification via Inter-Class Image Mixup with Diffusion Model","created":"2024-03-28","cited_by_count":34,"area":"diffusion"},{"id":"2310.00158","title":"Feedback-guided Data Synthesis for Imbalanced Classification","created":"2023-09-29","cited_by_count":33,"area":"synth"},{"id":"2407.10910","title":"DataDream: Few-shot Guided Dataset Generation","created":"2024-07-15","cited_by_count":29,"area":"diffusion"},{"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":"2403.12448","title":"Do Generated Data Always Help Contrastive Learning?","created":"2024-03-19","cited_by_count":25,"area":"diffusion"},{"id":"2404.03242","title":"Would Deep Generative Models Amplify Bias in Future Models?","created":"2024-04-04","cited_by_count":24,"area":null},{"id":"2406.08249","title":"Dataset Enhancement with Instance-Level Augmentations","created":"2024-06-12","cited_by_count":23,"area":"diffusion"},{"id":"2403.18775","title":"ImageNet-D: Benchmarking Neural Network Robustness on Diffusion Synthetic Object","created":"2024-03-27","cited_by_count":22,"area":"diffusion"},{"id":"2409.03550","title":"DKDM: Data-Free Knowledge Distillation for Diffusion Models with Any Architecture","created":"2024-09-05","cited_by_count":22,"area":"diffusion"},{"id":"2503.04229","title":"Synthetic Data is an Elegant GIFT for Continual Vision-Language Models","created":"2025-03-06","cited_by_count":21,"area":"mllm"},{"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":"2410.07838","title":"Minority-Focused Text-to-Image Generation via Prompt Optimization","created":"2024-10-10","cited_by_count":18,"area":"diffusion"},{"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":"2311.18158","title":"HiPA: Enabling One-Step Text-to-Image Diffusion Models via High-Frequency-Promoting Adaptation","created":"2023-11-30","cited_by_count":16,"area":"diffusion"},{"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":"2312.04566","title":"Gen2Det: Generate to Detect","created":"2023-12-07","cited_by_count":12,"area":"diffusion"},{"id":"2312.12080","title":"Learning Subject-Aware Cropping by Outpainting Professional Photos","created":"2023-12-19","cited_by_count":12,"area":"diffusion"},{"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":"2503.01167","title":"Enhancing Vision-Language Compositional Understanding with Multimodal Synthetic Data","created":"2025-03-03","cited_by_count":12,"area":"synth"},{"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":"2405.00557","title":"Mixture of insighTful Experts (MoTE): The Synergy of Thought Chains and Expert Mixtures in Self-Alignment","created":"2024-05-01","cited_by_count":10,"area":"lr"},{"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":"2404.13784","title":"Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images","created":"2024-04-21","cited_by_count":9,"area":"mllm"},{"id":"2405.20494","title":"Slight Corruption in Pre-training Data Makes Better Diffusion Models","created":"2024-05-30","cited_by_count":9,"area":"diffusion"},{"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":"2408.00350","title":"A Simple Background Augmentation Method for Object Detection with Diffusion Model","created":"2024-08-01","cited_by_count":9,"area":"diffusion"},{"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":"2503.10687","title":"Context-guided Responsible Data Augmentation with Diffusion Models","created":"2025-03-12","cited_by_count":9,"area":"diffusion"},{"id":"2312.02548","title":"GeNIe: Generative Hard Negative Images Through Diffusion","created":"2023-12-05","cited_by_count":8,"area":"diffusion"},{"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":"2312.05387","title":"Cross Domain Generative Augmentation: Domain Generalization with Latent Diffusion Models","created":"2023-12-08","cited_by_count":8,"area":"diffusion"},{"id":"2403.11111","title":"Diffusion Models are Efficient Data Generators for Human Mesh Recovery","created":"2024-03-17","cited_by_count":8,"area":"diffusion"},{"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":"2411.07205","title":"DLCR: A Generative Data Expansion Framework via Diffusion for Clothes-Changing Person Re-ID","created":"2024-11-11","cited_by_count":8,"area":"diffusion"},{"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":"2508.12026","title":"Bongard-RWR+: Real-World Representations of Fine-Grained Concepts in Bongard Problems","created":"2025-08-16","cited_by_count":7,"area":"lr"},{"id":"2311.16122","title":"Semantic Generative Augmentations for Few-Shot Counting","created":"2023-10-26","cited_by_count":6,"area":"diffusion"},{"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":"2410.09865","title":"SynFER: Towards Boosting Facial Expression Recognition with Synthetic Data","created":"2024-10-13","cited_by_count":6,"area":"synth"},{"id":"2506.23731","title":"Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models","created":"2025-06-30","cited_by_count":6,"area":"safety"},{"id":"2510.16657","title":"Escaping Model Collapse via Synthetic Data Verification: Near-term Improvements and Long-term Convergence","created":"2025-10-18","cited_by_count":6,"area":"synth"},{"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":"2602.19946","title":"When Pretty Isn't Useful: Investigating Why Modern Text-to-Image Models Fail as Reliable Training Data Generators","created":"2026-02-23","cited_by_count":6,"area":"diffusion"},{"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":"2405.03243","title":"Mind the Gap Between Synthetic and Real: Utilizing Transfer Learning to Probe the Boundaries of Stable Diffusion Generated Data","created":"2024-05-06","cited_by_count":5,"area":"diffusion"},{"id":"2412.01672","title":"Gen-SIS: Generative Self-augmentation Improves Self-supervised Learning","created":"2024-12-02","cited_by_count":5,"area":"diffusion"},{"id":"2503.21449","title":"Towards Generating Realistic 3D Semantic Training Data for Autonomous Driving","created":"2025-03-27","cited_by_count":5,"area":"wm"},{"id":"2511.12449","title":"MOON2.0: Dynamic Modality-balanced Multimodal Representation Learning for E-commerce Product Understanding","created":"2025-11-16","cited_by_count":5,"area":"mllm"},{"id":"2309.01369","title":"Exploring Limits of Diffusion-Synthetic Training with Weakly Supervised Semantic Segmentation","created":"2023-09-04","cited_by_count":4,"area":"diffusion"},{"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":"2404.16637","title":"Zero-Shot Distillation for Image Encoders: How to Make Effective Use of Synthetic Data","created":"2024-04-25","cited_by_count":4,"area":"synth"},{"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":"2406.20085","title":"Auto Cherry-Picker: Learning from High-quality Generative Data Driven by Language","created":"2024-06-28","cited_by_count":4,"area":"diffusion"},{"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":"2503.12563","title":"Diffusion on Graph: Augmentation of Graph Structure for Node Classification","created":"2025-03-16","cited_by_count":4,"area":"diffusion"},{"id":"2504.11457","title":"Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception","created":"2025-04-15","cited_by_count":4,"area":"diffusion"},{"id":"2403.05966","title":"Can Generative Models Improve Self-Supervised Representation Learning?","created":"2024-03-09","cited_by_count":3,"area":null},{"id":"2406.11331","title":"They're All Doctors: Synthesizing Diverse Counterfactuals to Mitigate Associative Bias","created":"2024-06-17","cited_by_count":3,"area":"mllm"},{"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":"2410.21826","title":"Volumetric Conditioning Module to Control Pretrained Diffusion Models for 3D Medical Images","created":"2024-10-29","cited_by_count":3,"area":"diffusion"},{"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}],"next_cursor":"100"}