{"total":34,"rows":[{"id":"2506.02314","title":"ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code","created":"2025-06-02","cited_by_count":36,"area":null},{"id":"2505.19825","title":"Position: Foundation Models for Tabular Data within Systemic Contexts Need Grounding","created":"2025-05-26","cited_by_count":6,"area":null},{"id":"2601.23068","title":"ExplainerPFN: Towards tabular foundation models for model-free zero-shot feature importance estimations","created":"2026-01-30","cited_by_count":5,"area":null},{"id":"2506.14206","title":"CausalDiffTab: Mixed-Type Causal-Aware Diffusion for Tabular Data Generation","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2501.01216","title":"TabTreeFormer: Tabular Data Generation Using Hybrid Tree-Transformer","created":"2025-01-02","cited_by_count":2,"area":null},{"id":"2604.22337","title":"TabSCM: A practical Framework for Generating Realistic Tabular Data","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2607.03926","title":"TabQueryBench: A Query-Centric Benchmark for Synthetic Tabular Data","created":"2026-07-04","cited_by_count":2,"area":null},{"id":"2607.21636","title":"Measuring the Dependency Gap: Diagnosing Inter-Column Fidelity in Tabular Generative Models","created":"2026-07-20","cited_by_count":2,"area":null},{"id":"2601.22434","title":"Rethinking Anonymity Claims in Synthetic Data Generation: A Model-Centric Privacy Attack Perspective","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2602.04785","title":"Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2603.23016","title":"A Sobering Look at Tabular Data Generation via Probabilistic Circuits","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2605.04911","title":"Breaking the Quality-Privacy Tradeoff in Tabular Data Generation via In-Context Learning","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2605.06261","title":"Inference-Time Refinement Closes the Synthetic-Real Gap in Tabular Diffusion","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2608.18849","title":"GEAR: Generative Expansion and Real Anchoring for Two-Stage Distillation of Tabular Foundation Models","created":"2026-08-19","cited_by_count":1,"area":null},{"id":"2504.18544","title":"Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review","created":"2025-04-10","cited_by_count":0,"area":null},{"id":"2507.19700","title":"Disjoint Generation of Synthetic Data","created":"2025-07-25","cited_by_count":0,"area":null},{"id":"2511.23220","title":"Instruction Tuning of Large Language Models for Tabular Data Generation-in One Day","created":"2025-11-28","cited_by_count":0,"area":null},{"id":"2601.20854","title":"Exploring Transformer Placement in Variational Autoencoders for Tabular Data Generation","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.03641","title":"CTTVAE: Latent Space Structuring for Conditional Tabular Data Generation on Imbalanced Datasets","created":"2026-02-03","cited_by_count":0,"area":null},{"id":"2602.07875","title":"Harpoon: Generalised Manifold Guidance for Conditional Tabular Diffusion","created":"2026-02-08","cited_by_count":0,"area":null},{"id":"2602.09288","title":"Measuring Privacy Risks and Tradeoffs in Financial Synthetic Data Generation","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.01444","title":"Autoregressive Synthesis of Sparse and Semi-Structured Mixed-Type Data","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2603.23719","title":"CDMT-EHR: A Continuous-Time Diffusion Framework for Generating Mixed-Type Time-Series Electronic Health Records","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.09091","title":"Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.06835","title":"On Privacy in Data-Space Tabular Diffusion Models: Influential Factors, Attacker Knowledge, and Metrics","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.13551","title":"Mixed neural posterior estimation for simulators with discrete and continuous parameters","created":"2026-05-13","cited_by_count":0,"area":null},{"id":"2605.17642","title":"TabKDE: Simple and Scalable Tabular Data Generation with Kernel Density Estimates","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.05361","title":"TabSODA: Tabular Diffusion based Imputation with Skip Pattern Detection and Ordinal Awareness","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.06990","title":"Accelerating Reproducible Research in Synthetic EHR Generation","created":"2026-06-05","cited_by_count":0,"area":null},{"id":"2606.21820","title":"Generating Public Health Responses using Survey-Augmented Large Language Models","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2608.07881","title":"GRACE: LLM-Grounded Semantic Metric Spaces for Scalable Mixed-Data Clustering","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2610.03259","title":"PaMIR: Open Benchmark of Public Credit-Default Datasets","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.12586","title":"Realism VS Accuracy: Event Sequence Forecasting from a Generative Modeling Perspective","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.15699","title":"TabMosaic: Unified In-Context Diffusion for Tabular Generative Tasks","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}