{"total":21,"items":[{"citing_arxiv_id":"2606.22510","ref_index":32,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Fed-CausalDiff: Decoupled Synchronization for Federated Do-Simulation and Policy Evaluation","primary_cat":"cs.LG","submitted_at":"2026-06-21T14:04:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Fed-CausalDiff proposes decoupled synchronization in a federated causal diffusion model to improve do-simulation and policy-value estimation across heterogeneous decentralized datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.10466","ref_index":10,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation","primary_cat":"cs.LG","submitted_at":"2026-06-09T06:36:06+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"UPLOTS proposes a unified prompt-guided pretrained transformer for generating constrained time-series data across diverse domains using dynamic multi-dataset loss re-weighting.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08736","ref_index":13,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark","primary_cat":"cs.LG","submitted_at":"2026-06-07T17:10:40+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Defines outcome-conformant synthesis as exact closed-form generation of relational data matching declared aggregates via Gamma conditional-sum sampling, introduces SpecBench for measuring conformance, and shows it is orthogonal to fidelity.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.06007","ref_index":25,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Diffusion Models for Adaptive Sequential Data Generation","primary_cat":"cs.LG","submitted_at":"2026-06-04T10:59:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Introduces a sequential forward-backward diffusion framework that generates adapted time series by conditioning on prior history, with a parallelizable score-matching objective and statistical guarantees for ReLU networks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05138","ref_index":111,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Generating Financial Time Series by Matching Random Convolutional Features","primary_cat":"cs.LG","submitted_at":"2026-06-03T17:46:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces SOCK (SOft Competing Kernels), a differentiable random convolutional feature map, to train generative models of financial time series via feature matching and shows outperformance over signature and diffusion baselines on small-sample datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.05264","ref_index":44,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"REGEN: Reference-Guided Synthetic Multivariate Time Series Generation for Forecasting","primary_cat":"cs.LG","submitted_at":"2026-06-03T16:19:55+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"ReGeN decomposes references into periodic, stochastic, and causal components to generate synthetic multivariate time series that preserve domain structure and support improved forecasting in low-data settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.03347","ref_index":1,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking","primary_cat":"cs.LG","submitted_at":"2026-06-02T08:57:38+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"AugMask is a plug-and-play training framework that lets diffusion models on incomplete tabular data use stochastic augmentation for conditioning and observed-only supervision, outperforming missing-aware baselines via a Rao-Blackwellized objective.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.00708","ref_index":46,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MOSAIC: Modular Orchestration for Structured Agentic Intelligence and Composition","primary_cat":"cs.AI","submitted_at":"2026-05-30T12:31:13+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MOSAIC structures LLM-based model selection via memory-grounded blueprints and failure-aware RL, reporting gains in performance and traceability on financial time-series tasks over AutoML and agent baselines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27892","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"FedEHR-Gen: Federated Synthetic Time-Series EHR Generation via Latent Space Alignment and Distribution-Aware Aggregation","primary_cat":"cs.LG","submitted_at":"2026-05-27T03:17:08+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FedEHR-Gen is a federated two-stage autoencoder plus TCVAE system that aligns latent spaces via layer-wise matching and uses distribution-aware aggregation to produce synthetic EHR time-series data matching centralized performance on eICU and MIMIC-III.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.27113","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:52:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Hybrid CoMeTS-GAN plus diffusion model generates multivariate financial time series claimed to better reproduce stylized facts and inter-asset correlations than prior generative methods.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.07569","ref_index":17,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"TriHead-GAN: A Generative Adversarial Network with Triple-Head Discriminator for Carbon Emission Time Series Generation","primary_cat":"cs.LG","submitted_at":"2026-05-26T02:48:56+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"TriHead-GAN is a GAN framework whose triple-head discriminator supervises distributional authenticity, cross-variable dependency via regression, and temporal smoothness via adjacent-difference prediction for carbon emission time series.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.28867","ref_index":28,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"PrismFlow: Residual Dynamics for Flow Matching in Time-Series Generation","primary_cat":"cs.LG","submitted_at":"2026-05-22T07:10:20+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"PrismFlow augments flow matching with residual dynamical experts and a winner-take-all objective to reduce spectral distortion and improve mode coverage in time-series generation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17804","ref_index":15,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"GenTS: A Comprehensive Benchmark Library for Generative Time Series Models","primary_cat":"cs.LG","submitted_at":"2026-05-18T03:27:54+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"GenTS is a modular benchmark library providing unified data pipelines, generative models, and evaluation metrics for time series synthesis, forecasting, and imputation, with open-source code and initial benchmarking experiments.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.00788","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Repurposing Image Diffusion Models for Adversarial Synthetic Structured Data: A Case Study of Ground Truth Drift","primary_cat":"cs.CR","submitted_at":"2026-05-01T17:11:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Off-the-shelf image diffusion models can be repurposed to create synthetic structured data capable of inducing ground truth drift in machine pipelines.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.27182","ref_index":54,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Preserving Temporal Dynamics in Time Series Generation","primary_cat":"cs.LG","submitted_at":"2026-04-29T20:32:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"An MCMC framework enforces empirical transition laws on GAN outputs to reduce temporal drift in synthetic multivariate time series.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.22337","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"TabSCM: A practical Framework for Generating Realistic Tabular Data","primary_cat":"cs.LG","submitted_at":"2026-04-24T08:10:01+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"TabSCM produces causally consistent tabular data by orienting a CPDAG into a DAG, fitting root marginals with KDE, and using conditional diffusion plus trees for child nodes, outperforming GANs and diffusion baselines on fidelity, utility, and privacy across seven datasets.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.19653","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Dual Perspective on Synthetic Trajectory Generators: Utility Framework and Privacy Vulnerabilities","primary_cat":"cs.AI","submitted_at":"2026-04-21T16:42:33+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A new framework evaluates utility of synthetic mobility trajectories while a membership inference attack reveals privacy vulnerabilities in generative models thought to be safe.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"synthetic trajectory information that cannot be linked back to any real person. There are a variety of solutions to perform this dual task [22, 25, 52, 67, 92].This paper focuses on advances in deep neu- ral networks as generative models for human mobility data [47, 103]. To produce synthetic datasets, deep learning solutions have been shown to produce better convincing results than traditional tech- niques [32, 59]. Although there is an extensive literature that proposes a range of architectures to build generative models [19, 22, 32, 92, 121, 122], there is no standard way to evaluate their performances. Most of them evaluate their utility through a sample of utility metrics, making comparison between architectures difficult [ 32, 92, 121]. The distributions of individual mobility datasets are inherently"},{"citing_arxiv_id":"2604.16182","ref_index":48,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Synthetic data in cryptocurrencies using generative models","primary_cat":"cs.LG","submitted_at":"2026-04-17T15:48:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":3.0,"formal_verification":"none","one_line_summary":"CGANs with LSTM generator can produce synthetic crypto price series that reproduce temporal patterns and preserve market trends and dynamics.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.13685","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"EMGFlow: Robust and Efficient Surface Electromyography Synthesis via Flow Matching","primary_cat":"cs.HC","submitted_at":"2026-04-15T10:07:29+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"EMGFlow is the first application of flow matching to synthesize sEMG data, outperforming GAN and diffusion baselines in fidelity, distributional metrics, and downstream gesture recognition utility under TSTR evaluation.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2509.20846","ref_index":11,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"Causal Time Series Generation via Diffusion Models","primary_cat":"cs.LG","submitted_at":"2025-09-25T07:34:46+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"CaTSG is a unified diffusion model for causal time series generation that handles observational, interventional, and counterfactual tasks via backdoor adjustment and abduction-action-prediction.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.14202","ref_index":16,"ref_count":1,"confidence":0.98,"is_internal_anchor":true,"paper_title":"MSDformer: Multi-scale Discrete Transformer For Time Series Generation","primary_cat":"cs.LG","submitted_at":"2025-05-20T11:01:36+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"MSDformer introduces a multi-scale discrete transformer that tokenizes time series at multiple scales and models them autoregressively in discrete space, claiming superior performance over prior DTM methods with rate-distortion theoretical support.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}