{"total":120,"rows":[{"id":"2404.07503","title":"Best Practices and Lessons Learned on Synthetic Data","created":"2024-04-11","cited_by_count":106,"area":"synth"},{"id":"2501.04686","title":"Unlocking Multimodal Mathematical Reasoning via Process Reward Model","created":"2025-01-08","cited_by_count":65,"area":"lr"},{"id":"2312.00825","title":"SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examples","created":"2023-11-30","cited_by_count":53,"area":"mllm"},{"id":"2505.10557","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning","created":"2025-05-15","cited_by_count":45,"area":"lr"},{"id":"2405.10853","title":"The Future of Large Language Model Pre-training is Federated","created":"2024-05-17","cited_by_count":30,"area":null},{"id":"2408.02085","title":"Unleashing the Power of Data Tsunami: A Comprehensive Survey on Data Assessment and Selection for Instruction Tuning of Language Models","created":"2024-08-04","cited_by_count":29,"area":"alignment"},{"id":"2305.15407","title":"Balancing the Picture: Debiasing Vision-Language Datasets with Synthetic Contrast Sets","created":"2023-05-24","cited_by_count":27,"area":"mllm"},{"id":"2404.01273","title":"TWIN-GPT: Digital Twins for Clinical Trials via Large Language Model","created":"2024-04-01","cited_by_count":24,"area":null},{"id":"2310.16981","title":"Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark","created":"2023-10-25","cited_by_count":23,"area":null},{"id":"2401.03482","title":"Uncertainty Quantification on Clinical Trial Outcome Prediction","created":"2024-01-07","cited_by_count":19,"area":null},{"id":"2310.17876","title":"TarGEN: Targeted Data Generation with Large Language Models","created":"2023-10-27","cited_by_count":17,"area":null},{"id":"2402.01096","title":"Trustworthy Distributed AI Systems: Robustness, Privacy, and Governance","created":"2024-02-02","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":"2410.14208","title":"Montessori-Instruct: Generate Influential Training Data Tailored for Student Learning","created":"2024-10-18","cited_by_count":13,"area":null},{"id":"2504.11967","title":"Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directions","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2402.01712","title":"Socially Aware Synthetic Data Generation for Suicidal Ideation Detection Using Large Language Models","created":"2024-01-25","cited_by_count":10,"area":null},{"id":"2509.26614","title":"Hy-Facial: Hybrid Feature Extraction by Dimensionality Reduction Methods for Enhanced Facial Expression Classification","created":"2025-09-30","cited_by_count":10,"area":null},{"id":"2504.10563","title":"Data Augmentation Through Random Style Replacement","created":"2025-04-14","cited_by_count":9,"area":null},{"id":"2411.02947","title":"Time-Causal VAE: Robust Financial Time Series Generator","created":"2024-11-05","cited_by_count":8,"area":null},{"id":"2307.02819","title":"Trends in Machine Learning and Electroencephalogram (EEG): A Review for Undergraduate Researchers","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2308.00454","title":"ViT2EEG: Leveraging Hybrid Pretrained Vision Transformers for EEG Data","created":"2023-08-01","cited_by_count":7,"area":null},{"id":"2406.10292","title":"Automatically Labeling Clinical Trial Outcomes: A Large-Scale Benchmark for Drug Development","created":"2024-06-13","cited_by_count":7,"area":null},{"id":"2406.19614","title":"A Survey on Data Quality Dimensions and Tools for Machine Learning","created":"2024-06-28","cited_by_count":7,"area":null},{"id":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2401.10744","title":"FinLLMs: A Framework for Financial Reasoning Dataset Generation with Large Language Models","created":"2024-01-19","cited_by_count":6,"area":"lr"},{"id":"2411.03351","title":"Tabular Data Synthesis with Differential Privacy: A Survey","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2510.26046","title":"Bias-Corrected Data Synthesis for Imbalanced Learning","created":"2025-10-30","cited_by_count":6,"area":"synth"},{"id":"2510.26582","title":"CATCH: A Modular Cross-domain Adaptive Template with Hook","created":"2025-10-30","cited_by_count":6,"area":"lr"},{"id":"2411.10156","title":"Mitigating Sycophancy in Decoder-Only Transformer Architectures: Synthetic Data Intervention","created":"2024-11-15","cited_by_count":5,"area":"alignment"},{"id":"2510.26076","title":"New Money: A Systematic Review of Synthetic Data Generation for Finance","created":"2025-10-30","cited_by_count":5,"area":null},{"id":"2407.02716","title":"Light-weight Fine-tuning Method for Defending Adversarial Noise in Pre-trained Medical Vision-Language Models","created":"2024-07-02","cited_by_count":4,"area":"mllm"},{"id":"2410.00759","title":"Targeted synthetic data generation for tabular data via hardness characterization","created":"2024-10-01","cited_by_count":4,"area":null},{"id":"2501.01785","title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","created":"2025-01-03","cited_by_count":4,"area":null},{"id":"2501.16353","title":"Synthetic Data Generation by Supervised Neural Gas Network for Physiological Emotion Recognition Data","created":"2025-01-19","cited_by_count":4,"area":null},{"id":"2406.00505","title":"Improving Text Generation on Images with Synthetic Captions","created":"2024-06-01","cited_by_count":3,"area":"diffusion"},{"id":"2508.07876","title":"Stochastic dynamics learning with state-space systems","created":"2025-08-11","cited_by_count":3,"area":null},{"id":"2603.05396","title":"Harnessing Synthetic Data from Generative AI for Statistical Inference","created":"2026-03-05","cited_by_count":3,"area":null},{"id":"2308.07645","title":"Steering Language Generation: Harnessing Contrastive Expert Guidance and Negative Prompting for Coherent and Diverse Synthetic Data Generation","created":"2023-08-15","cited_by_count":2,"area":"synth"},{"id":"2312.14249","title":"GenoCraft: A Comprehensive, User-Friendly Web-Based Platform for High-Throughput Omics Data Analysis and Visualization","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2404.15311","title":"Fusing Pretrained ViTs with TCNet for Enhanced EEG Regression","created":"2024-04-02","cited_by_count":2,"area":null},{"id":"2405.16971","title":"A Unified Framework for Tabular Generative Modeling: Loss Functions, Benchmarks, and Improved Multi-objective Bayesian Optimization Approaches","created":"2024-05-27","cited_by_count":2,"area":null},{"id":"2409.14785","title":"Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models","created":"2024-09-23","cited_by_count":2,"area":"mllm"},{"id":"2411.06870","title":"AI-Native Multi-Access Future Networks -- The REASON Architecture","created":"2024-11-11","cited_by_count":2,"area":null},{"id":"2411.18071","title":"Simulating Tabular Datasets through LLMs to Rapidly Explore Hypotheses about Real-World Entities","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2412.00055","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","created":"2024-11-24","cited_by_count":2,"area":null},{"id":"2503.14513","title":"Synthetic Data Generation of Body Motion Data by Neural Gas Network for Emotion Recognition","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2503.24062","title":"Artificial Conversations, Real Results: Fostering Language Detection with Synthetic Data","created":"2025-03-31","cited_by_count":2,"area":"synth"},{"id":"2504.13519","title":"Filter2Noise: A Framework for Interpretable and Zero-Shot Low-Dose CT Image Denoising","created":"2025-04-18","cited_by_count":2,"area":null},{"id":"2505.15087","title":"HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions","created":"2025-05-21","cited_by_count":2,"area":null},{"id":"2508.21179","title":"Synthetic CVs To Build and Test Fairness-Aware Hiring Tools","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2510.08095","title":"Beyond Real Data: Synthetic Data through the Lens of Regularization","created":"2025-10-09","cited_by_count":2,"area":null},{"id":"2511.04478","title":"Generate, Evaluate, Iterate: Synthetic Data for Human-in-the-Loop Refinement of LLM Judges","created":"2025-11-06","cited_by_count":2,"area":"synth"},{"id":"2604.07486","title":"Private Seeds, Public LLMs: Realistic and Privacy-Preserving Synthetic Data Generation","created":"2026-04-08","cited_by_count":2,"area":"synth"},{"id":"2605.17558","title":"Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.20151","title":"When Does Model Collapse Occur in Structured Interactive Learning?","created":"2026-05-19","cited_by_count":2,"area":"synth"},{"id":"2401.00393","title":"Generative Model-Driven Synthetic Training Image Generation: An Approach to Cognition in Rail Defect Detection","created":"2023-12-31","cited_by_count":1,"area":null},{"id":"2404.12730","title":"PATE-TripleGAN: Privacy-Preserving Image Synthesis with Gaussian Differential Privacy","created":"2024-04-19","cited_by_count":1,"area":null},{"id":"2404.14754","title":"Skip the Benchmark: Generating System-Level High-Level Synthesis Data using Generative Machine Learning","created":"2024-04-23","cited_by_count":1,"area":null},{"id":"2406.10940","title":"From Data Quality for AI to AI for Data Quality: A Systematic Review of Tools for AI-Augmented Data Quality Management in Data Warehouses","created":"2024-06-16","cited_by_count":1,"area":null},{"id":"2408.03480","title":"Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-Processing","created":"2024-08-06","cited_by_count":1,"area":null},{"id":"2410.07825","title":"Extracting and Combining Abilities For Building Multi-lingual Ability-enhanced Large Language Models","created":"2024-10-10","cited_by_count":1,"area":null},{"id":"2410.17959","title":"Medical Imaging Complexity and its Effects on GAN Performance","created":"2024-10-23","cited_by_count":1,"area":null},{"id":"2501.10677","title":"Class-Imbalanced-Aware Adaptive Dataset Distillation for Scalable Pretrained Model on Credit Scoring","created":"2025-01-18","cited_by_count":1,"area":null},{"id":"2501.17206","title":"Integrating Reinforcement Learning and AI Agents for Adaptive Robotic Interaction and Assistance in Dementia Care","created":"2025-01-28","cited_by_count":1,"area":"agents"},{"id":"2502.18644","title":"Steered Generation via Gradient Descent on Sparse Features","created":"2025-02-25","cited_by_count":1,"area":null},{"id":"2504.17203","title":"High-Fidelity And Complex Test Data Generation For Google SQL Code Generation Services","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2504.21634","title":"Quantitative Auditing of AI Fairness with Differentially Private Synthetic Data","created":"2025-04-30","cited_by_count":1,"area":null},{"id":"2506.03522","title":"Path Generation and Evaluation in Video Games: A Nonparametric Statistical Approach","created":"2025-06-04","cited_by_count":1,"area":null},{"id":"2507.15132","title":"Transforming Datasets to Requested Complexity with Projection-based Many-Objective Genetic Algorithm","created":"2025-07-20","cited_by_count":1,"area":null},{"id":"2509.10108","title":"Scaling Arabic Medical Chatbots Using Synthetic Data: Enhancing Generative AI with Synthetic Patient Records","created":"2025-09-12","cited_by_count":1,"area":"synth"},{"id":"2510.23443","title":"A Neuro-Symbolic Multi-Agent Approach to Legal-Cybersecurity Knowledge Integration","created":"2025-10-27","cited_by_count":1,"area":null},{"id":"2511.07997","title":"PrAda-GAN: A Private Adaptive Generative Adversarial Network with Bayes Network Structure","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2603.02969","title":"Integrating Homomorphic Encryption and Synthetic Data in FL for Privacy and Learning Quality","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.22467","title":"Auditing Metrics for Synthetic Data Utility: A Cross-Domain Study of Appearance and Geometry","created":"2026-05-21","cited_by_count":1,"area":null},{"id":"2311.09854","title":"SurvTimeSurvival: Survival Analysis On The Patient With Multiple Visits/Records","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2402.16910","title":"NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification","created":"2024-02-25","cited_by_count":0,"area":null},{"id":"2403.06088","title":"Towards In-Vehicle Multi-Task Facial Attribute Recognition: Investigating Synthetic Data and Vision Foundation Models","created":"2024-03-10","cited_by_count":0,"area":"synth"},{"id":"2404.09846","title":"A Diffusion-based Data Generator for Training Object Recognition Models in Ultra-Range Distance","created":"2024-04-15","cited_by_count":0,"area":null},{"id":"2406.10255","title":"WarCov -- Large multilabel and multimodal dataset from social platform","created":"2024-06-10","cited_by_count":0,"area":null},{"id":"2408.03449","title":"EEGMobile: Enhancing Speed and Accuracy in EEG-Based Gaze Prediction with Advanced Mobile Architectures","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2408.03472","title":"Integrating HCI Datasets in Project-Based Machine Learning Courses: A College-Level Review and Case Study","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2408.03478","title":"Effect of Kernel Size on CNN-Vision-Transformer-Based Gaze Prediction Using Electroencephalography Data","created":"2024-08-06","cited_by_count":0,"area":null},{"id":"2408.12888","title":"Accelerated Markov Chain Monte Carlo Using Adaptive Weighting Scheme","created":"2024-08-23","cited_by_count":0,"area":null},{"id":"2409.07089","title":"TrialSynth: Generation of Synthetic Sequential Clinical Trial Data","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2409.20149","title":"1 Trillion Token (1TT) Platform: A Novel Framework for Efficient Data Sharing and Compensation in Large Language Models","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2411.01929","title":"Exploring the Landscape for Generative Sequence Models for Specialized Data Synthesis","created":"2024-11-04","cited_by_count":0,"area":"synth"},{"id":"2412.01948","title":"The Evolution and Future Perspectives of Artificial Intelligence Generated Content","created":"2024-12-02","cited_by_count":0,"area":null},{"id":"2412.16499","title":"Autonomous Crack Detection using Deep Learning on Synthetic Thermogram Datasets","created":"2024-12-21","cited_by_count":0,"area":null},{"id":"2502.10001","title":"EmbBERT: Attention Under 2 MB Memory","created":"2025-02-14","cited_by_count":0,"area":null},{"id":"2503.06444","title":"Towards Synthesizing High-Dimensional Tabular Data with Limited Samples","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2503.22569","title":"Comparing Methods for Bias Mitigation in Graph Neural Networks","created":"2025-03-28","cited_by_count":0,"area":null},{"id":"2504.02269","title":"Engineering Artificial Intelligence: Framework, Challenges, and Future Direction","created":"2025-04-03","cited_by_count":0,"area":null},{"id":"2504.06055","title":"A Trustworthy By Design Classification Model for Building Energy Retrofit Decision Support","created":"2025-04-08","cited_by_count":0,"area":null},{"id":"2504.08852","title":"ML For Hardware Design Interpretability: Challenges and Opportunities","created":"2025-04-11","cited_by_count":0,"area":null},{"id":"2506.17847","title":"A Comparative Study of Open-Source Libraries for Synthetic Tabular Data Generation: SDV vs. SynthCity","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2508.10000","title":"AutoGeTS: Knowledge-based Automated Generation of Text Synthetics for Improving Text Classification","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.10915","title":"Insect-Wing Structured Microfluidic System for Reservoir Computing","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2508.15180","title":"PuzzleClone: A DSL-Powered Framework for Synthesizing Verifiable Data","created":"2025-08-21","cited_by_count":0,"area":"lr"},{"id":"2508.16254","title":"FEST: A Unified Framework for Evaluating Synthetic Tabular Data","created":"2025-08-22","cited_by_count":0,"area":null},{"id":"2509.01387","title":"ABCD-LINK: Annotation Bootstrapping for Cross-Document Fine-Grained Links","created":"2025-09-01","cited_by_count":0,"area":"synth"}],"next_cursor":"100"}