{"total":108,"rows":[{"id":"2402.07043","title":"A Tale of Tails: Model Collapse as a Change of Scaling Laws","created":"2024-02-10","cited_by_count":130,"area":"synth"},{"id":"2411.04330","title":"Scaling Laws for Precision","created":"2024-11-07","cited_by_count":95,"area":null},{"id":"2402.07712","title":"Model Collapse Demystified: The Case of Regression","created":"2024-02-12","cited_by_count":82,"area":"synth"},{"id":"2312.17742","title":"Learning Vision from Models Rivals Learning Vision from Data","created":"2023-12-28","cited_by_count":71,"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":"2404.18202","title":"WorldGPT: Empowering LLM as Multimodal World Model","created":"2024-04-28","cited_by_count":42,"area":"wm"},{"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":"2412.02980","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","created":"2024-12-04","cited_by_count":35,"area":"synth"},{"id":"2509.09555","title":"InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation","created":"2025-09-11","cited_by_count":32,"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":"2402.04376","title":"Scaling laws for learning with real and surrogate data","created":"2024-02-06","cited_by_count":27,"area":null},{"id":"2403.07750","title":"Synth$^2$: Boosting Visual-Language Models with Synthetic Captions and Image Embeddings","created":"2024-03-12","cited_by_count":18,"area":"mllm"},{"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":"2402.01909","title":"On Catastrophic Inheritance of Large Foundation Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"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":"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":"2510.14831","title":"Scaling Tumor Segmentation: Best Lessons from Real and Synthetic Data","created":"2025-10-16","cited_by_count":13,"area":null},{"id":"2406.14551","title":"Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation","created":"2024-06-20","cited_by_count":12,"area":null},{"id":"2406.19593","title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","created":"2024-06-28","cited_by_count":12,"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":"2412.16156","title":"Personalized Representation from Personalized Generation","created":"2024-12-20","cited_by_count":9,"area":null},{"id":"2506.21233","title":"ReME: A Data-Centric Framework for Training-Free Open-Vocabulary Segmentation","created":"2025-06-26","cited_by_count":9,"area":null},{"id":"2409.03901","title":"Onboard Satellite Image Classification for Earth Observation: A Comparative Study of ViT Models","created":"2024-09-05","cited_by_count":8,"area":null},{"id":"2408.04556","title":"BA-LoRA: Bias-Alleviating Low-Rank Adaptation to Mitigate Catastrophic Inheritance in Large Language Models","created":"2024-08-08","cited_by_count":7,"area":null},{"id":"2410.13523","title":"Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data?","created":"2024-10-17","cited_by_count":7,"area":"mllm"},{"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":"2510.08123","title":"High-dimensional Analysis of Synthetic Data Selection","created":"2025-10-09","cited_by_count":7,"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":"2410.13098","title":"A Little Human Data Goes A Long Way","created":"2024-10-17","cited_by_count":6,"area":null},{"id":"2509.08653","title":"Generative Data Refinement: Just Ask for Better Data","created":"2025-09-10","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":"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":"2404.02973","title":"Scaling Laws for Galaxy Images","created":"2024-04-03","cited_by_count":5,"area":null},{"id":"2405.18029","title":"Are Images Indistinguishable to Humans Also Indistinguishable to Classifiers?","created":"2024-05-28","cited_by_count":5,"area":"diffusion"},{"id":"2409.16949","title":"DALDA: Data Augmentation Leveraging Diffusion Model and LLM with Adaptive Guidance Scaling","created":"2024-09-25","cited_by_count":5,"area":"diffusion"},{"id":"2503.09122","title":"Training Data Provenance Verification: Did Your Model Use Synthetic Data from My Generative Model for Training?","created":"2025-03-12","cited_by_count":4,"area":"diffusion"},{"id":"2505.10551","title":"Does Feasibility Matter? Understanding the Impact of Feasibility on Synthetic Training Data","created":"2025-05-15","cited_by_count":4,"area":"diffusion"},{"id":"2403.05170","title":"DiffuLT: How to Make Diffusion Model Useful for Long-tail Recognition","created":"2024-03-08","cited_by_count":3,"area":"diffusion"},{"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":"2408.14559","title":"Exploring the Potential of Synthetic Data to Replace Real Data","created":"2024-08-26","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":"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":"2411.17794","title":"NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?","created":"2024-11-26","cited_by_count":2,"area":"mllm"},{"id":"2501.18962","title":"Spend Wisely: Maximizing Post-Training Gains in Iterative Synthetic Data Bootstrapping","created":"2025-01-31","cited_by_count":2,"area":"synth"},{"id":"2503.06014","title":"Towards Ambiguity-Free Spatial Foundation Model: Rethinking and Decoupling Depth Ambiguity","created":"2025-03-08","cited_by_count":2,"area":null},{"id":"2507.13568","title":"LoRA-Loop: Closing the Synthetic Replay Cycle for Continual VLM Learning","created":"2025-07-17","cited_by_count":2,"area":"mllm"},{"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":"2606.00571","title":"On the Difficulty of Learning a Meta-network for Training Data Selection","created":"2026-05-30","cited_by_count":2,"area":null},{"id":"2404.00593","title":"LAESI: Leaf Area Estimation with Synthetic Imagery","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2406.06134","title":"DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection","created":"2024-06-10","cited_by_count":1,"area":"diffusion"},{"id":"2407.19823","title":"Analyzing and reducing the synthetic-to-real transfer gap in Music Information Retrieval: the task of automatic drum transcription","created":"2024-07-29","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":"2411.17584","title":"Pre-training for Action Recognition with Automatically Generated Fractal Datasets","created":"2024-11-26","cited_by_count":1,"area":null},{"id":"2412.08307","title":"Investigating the Scaling Effect of Instruction Templates for Training Multimodal Language Model","created":"2024-12-11","cited_by_count":1,"area":"mllm"},{"id":"2501.00744","title":"Assessing the Distributional Fidelity of Synthetic Chest X-rays using the Embedded Characteristic Score","created":"2025-01-01","cited_by_count":1,"area":null},{"id":"2502.04475","title":"Augmented Conditioning Is Enough For Effective Training Image Generation","created":"2025-02-06","cited_by_count":1,"area":"diffusion"},{"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":"2503.24229","title":"Pre-training with 3D Synthetic Data: Learning 3D Point Cloud Instance Segmentation from 3D Synthetic Scenes","created":"2025-03-31","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":"2507.17346","title":"Taming Latency and Bandwidth: A Theoretical Framework and Adaptive Algorithm for Communication-Constrained Training","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2507.21947","title":"Enhancing Generalization in Data-free Quantization via Mixup-class Prompting","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.09550","title":"Exploring the Equivalence of Closed-Set Generative and Real Data Augmentation in Image Classification","created":"2025-08-13","cited_by_count":1,"area":null},{"id":"2510.04770","title":"Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning","created":"2025-10-06","cited_by_count":1,"area":null},{"id":"2510.09110","title":"Synthetic Object Compositions for Scalable and Accurate Learning in Detection, Segmentation, and Grounding","created":"2025-10-10","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":"2512.03463","title":"Text-Printed Image: Bridging the Image-Text Modality Gap for Text-centric Training of Large Vision-Language Models","created":"2025-12-03","cited_by_count":1,"area":"mllm"},{"id":"2512.23227","title":"Anomaly Detection by Effectively Leveraging Synthetic Images","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2602.01370","title":"PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles","created":"2026-02-01","cited_by_count":1,"area":"mllm"},{"id":"2604.13685","title":"EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching","created":"2026-04-15","cited_by_count":1,"area":"diffusion"},{"id":"2605.15167","title":"Does Synthetic Layered Design Data Benefit Layered Design Decomposition?","created":"2026-05-14","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":"2406.04295","title":"Everything to the Synthetic: Diffusion-driven Test-time Adaptation via Synthetic-Domain Alignment","created":"2024-06-06","cited_by_count":0,"area":"diffusion"},{"id":"2406.05432","title":"Regularized Training with Generated Datasets for Name-Only Transfer of Vision-Language Models","created":"2024-06-08","cited_by_count":0,"area":"mllm"},{"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":"2410.12279","title":"Beyond Oversmoothing: Evaluating DDPM and MSE for Scalable Speech Synthesis in ASR","created":"2024-10-16","cited_by_count":0,"area":"diffusion"},{"id":"2412.18460","title":"GeFL: Model-Agnostic Federated Learning with Generative Models","created":"2024-12-24","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":"2504.04510","title":"Attributed Synthetic Data Generation for Zero-shot Domain-specific Image Classification","created":"2025-04-06","cited_by_count":0,"area":"synth"},{"id":"2506.01987","title":"Equally Critical: Samples, Targets, and Their Mappings in Datasets","created":"2025-05-17","cited_by_count":0,"area":null},{"id":"2507.04270","title":"ZERO: Industry-ready Vision Foundation Model with Multi-modal Prompts","created":"2025-07-06","cited_by_count":0,"area":null},{"id":"2509.23594","title":"StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data","created":"2025-09-28","cited_by_count":0,"area":"synth"},{"id":"2509.26158","title":"Towards Continual Expansion of Data Coverage: Automatic Text-guided Edge-case Synthesis","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.10948","title":"Unify Variables in Neural Scaling Laws for General Audio Representations via Embedding Effective Rank","created":"2025-10-13","cited_by_count":0,"area":null},{"id":"2510.15194","title":"Salient Concept-Aware Generative Data Augmentation","created":"2025-10-16","cited_by_count":0,"area":null},{"id":"2510.24078","title":"Beyond Objects: Contextual Synthetic Data Generation for Fine-Grained Classification","created":"2025-10-28","cited_by_count":0,"area":null},{"id":"2602.12317","title":"Free Lunch in Medical Image Foundation Model Pre-training via Randomized Synthesis and Disentanglement","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2602.19708","title":"ChimeraLoRA: Multi-Head LoRA-Guided Synthetic Datasets","created":"2026-02-23","cited_by_count":0,"area":"diffusion"},{"id":"2603.04343","title":"Enhancing Authorship Attribution with Synthetic Paintings","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.05876","title":"Systematic Evaluation of Novel View Synthesis for Video Place Recognition","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.02946","title":"Learning from Synthetic Data via Provenance-Based Input Gradient Guidance","created":"2026-04-03","cited_by_count":0,"area":null},{"id":"2604.09531","title":"VisionFoundry: Teaching VLMs Visual Perception with Synthetic Images","created":"2026-04-10","cited_by_count":0,"area":"mllm"},{"id":"2604.12353","title":"Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.09699","title":"A Real-Calibrated Synthetic-First Data Engine","created":"2026-05-10","cited_by_count":0,"area":null},{"id":"2605.19289","title":"What Makes Synthetic Data Effective in Image Segmentation","created":"2026-05-19","cited_by_count":0,"area":"diffusion"},{"id":"2607.02637","title":"Post-Generation Curation of Synthetic Images via Homogeneous-Heterogeneous Splitting","created":"2026-07-02","cited_by_count":0,"area":null}],"next_cursor":"100"}