{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/task/synthetic-data-generation/papers/6","list_of":"/task/synthetic-data-generation","task":"Synthetic Data Generation","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":6,"pages_in_order":9,"rows_per_page":100,"rows":[501,600],"of":822,"counts":{"archive_papers_tagged":822,"with_a_code_link":325,"where_syntology_ran_a_sample":52,"not_listed_spam_title":0,"listed":822,"listed_where_code_ran":52,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":46,"every_run_a_failure_of_syntologys_instrument":6,"listed_with_a_run_with_no_instrument_failure":46,"listed_every_run_a_failure_of_syntologys_instrument":6,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/synthetic-data-generation","prev":"/task/synthetic-data-generation/papers/5","next":"/task/synthetic-data-generation/papers/7","papers":[{"url":"/paper/zgan-an-outlier-focused-generative","slug":"zgan-an-outlier-focused-generative","title":"zGAN: An Outlier-focused Generative Adversarial Network For Realistic Synthetic Data Generation","date":"2024-10-28","arxiv_id":"2410.20808","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-data-synthesis-a-teacher-model","title":"Rethinking Data Synthesis: A Teacher Model Training Recipe with Interpretation","date":"2024-10-27","arxiv_id":"2410.20362","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-hardened-and-hallucination-resistant","title":"Privacy-hardened and hallucination-resistant synthetic data generation with logic-solvers","date":"2024-10-22","arxiv_id":"2410.16705","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm4grn-discovering-causal-gene-regulatory","title":"LLM4GRN: Discovering Causal Gene Regulatory Networks with LLMs -- Evaluation through Synthetic Data Generation","date":"2024-10-21","arxiv_id":"2410.15828","repositories_listed":0,"syntology":null},{"url":null,"slug":"no-more-hard-prompts-softsrv-prompting-for","title":"No more hard prompts: SoftSRV prompting for synthetic data generation","date":"2024-10-21","arxiv_id":"2410.16534","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparkle-mastering-basic-spatial-capabilities","title":"Sparkle: Mastering Basic Spatial Capabilities in Vision Language Models Elicits Generalization to Composite Spatial Reasoning","date":"2024-10-21","arxiv_id":"2410.16162","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-for-residential","title":"Synthetic Data Generation for Residential Load Patterns via Recurrent GAN and Ensemble Method","date":"2024-10-20","arxiv_id":"2410.15379","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlled-automatic-task-specific-synthetic","title":"Controlled Automatic Task-Specific Synthetic Data Generation for Hallucination Detection","date":"2024-10-16","arxiv_id":"2410.12278","repositories_listed":0,"syntology":null},{"url":null,"slug":"consult-contrastive-self-supervised-learning","title":"CONSULT: Contrastive Self-Supervised Learning for Few-shot Tumor Detection","date":"2024-10-15","arxiv_id":"2410.11307","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-based-code-switched-text-generation-for","title":"LLM-based Code-Switched Text Generation for Grammatical Error Correction","date":"2024-10-14","arxiv_id":"2410.10349","repositories_listed":0,"syntology":null},{"url":null,"slug":"juree-not-judges-safeguarding-llm","title":"JurEE not Judges: safeguarding llm interactions with small, specialised Encoder Ensembles","date":"2024-10-11","arxiv_id":"2410.08442","repositories_listed":0,"syntology":null},{"url":null,"slug":"simplestrat-diversifying-language-model","title":"SimpleStrat: Diversifying Language Model Generation with Stratification","date":"2024-10-11","arxiv_id":"2410.09038","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-differentially-private-synthetic","title":"Evaluating Differentially Private Synthetic Data Generation in High-Stakes Domains","date":"2024-10-10","arxiv_id":"2410.08327","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-data-validation-methods-for","title":"Unsupervised Data Validation Methods for Efficient Model Training","date":"2024-10-10","arxiv_id":"2410.07880","repositories_listed":0,"syntology":null},{"url":null,"slug":"fill-in-the-gaps-model-calibration-and","title":"Fill In The Gaps: Model Calibration and Generalization with Synthetic Data","date":"2024-10-07","arxiv_id":"2410.10864","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-vulnerabilities-in-marginals-based","title":"Privacy Vulnerabilities in Marginals-based Synthetic Data","date":"2024-10-07","arxiv_id":"2410.05506","repositories_listed":0,"syntology":null},{"url":null,"slug":"auto-gda-automatic-domain-adaptation-for","title":"Auto-GDA: Automatic Domain Adaptation for Efficient Grounding Verification in Retrieval Augmented Generation","date":"2024-10-04","arxiv_id":"2410.03461","repositories_listed":0,"syntology":null},{"url":null,"slug":"dessie-disentanglement-for-articulated-3d","title":"Dessie: Disentanglement for Articulated 3D Horse Shape and Pose Estimation from Images","date":"2024-10-04","arxiv_id":"2410.03438","repositories_listed":0,"syntology":null},{"url":null,"slug":"restoring-super-high-resolution-gps-mobility","title":"Restoring Super-High Resolution GPS Mobility Data","date":"2024-10-01","arxiv_id":"2410.12818","repositories_listed":0,"syntology":null},{"url":null,"slug":"dopamine-domain-specific-pre-training","title":"DoPAMine: Domain-specific Pre-training Adaptation from seed-guided data Mining","date":"2024-09-30","arxiv_id":"2410.00260","repositories_listed":0,"syntology":null},{"url":null,"slug":"balancing-cost-and-effectiveness-of-synthetic","title":"Balancing Cost and Effectiveness of Synthetic Data Generation Strategies for LLMs","date":"2024-09-29","arxiv_id":"2409.19759","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-non-parametric-copulas","title":"Differentially Private Non Parametric Copulas: Generating synthetic data with non parametric copulas under privacy guarantees","date":"2024-09-27","arxiv_id":"2409.18611","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-data-point-generation-in-clustered","title":"Artificial Data Point Generation in Clustered Latent Space for Small Medical Datasets","date":"2024-09-26","arxiv_id":"2409.17685","repositories_listed":0,"syntology":null},{"url":null,"slug":"kipps-knowledge-infusion-in-privacy","title":"KIPPS: Knowledge infusion in Privacy Preserving Synthetic Data Generation","date":"2024-09-25","arxiv_id":"2409.17315","repositories_listed":0,"syntology":null},{"url":null,"slug":"manta-model-adapter-native-generations-that-s","title":"MANTA -- Model Adapter Native generations that's Affordable","date":"2024-09-22","arxiv_id":"2409.14363","repositories_listed":0,"syntology":null},{"url":null,"slug":"harnessing-llms-for-api-interactions-a","title":"Harnessing LLMs for API Interactions: A Framework for Classification and Synthetic Data Generation","date":"2024-09-18","arxiv_id":"2409.11703","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-large-language-models-into-world","title":"Making Large Language Models into World Models with Precondition and Effect Knowledge","date":"2024-09-18","arxiv_id":"2409.12278","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhanced-segmentation-of-femoral-bone","title":"Enhanced segmentation of femoral bone metastasis in CT scans of patients using synthetic data generation with 3D diffusion models","date":"2024-09-17","arxiv_id":"2409.11011","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-augmentation-for-robotic","title":"Synthetic data augmentation for robotic mobility aids to support blind and low vision people","date":"2024-09-17","arxiv_id":"2409.11164","repositories_listed":0,"syntology":null},{"url":null,"slug":"generated-data-with-fake-privacy-hidden","title":"Generated Data with Fake Privacy: Hidden Dangers of Fine-tuning Large Language Models on Generated Data","date":"2024-09-12","arxiv_id":"2409.11423","repositories_listed":0,"syntology":null},{"url":null,"slug":"source2synth-synthetic-data-generation-and","title":"Source2Synth: Synthetic Data Generation and Curation Grounded in Real Data Sources","date":"2024-09-12","arxiv_id":"2409.08239","repositories_listed":0,"syntology":null},{"url":null,"slug":"chain-of-translation-prompting-cotr-a-novel","title":"Chain-of-Translation Prompting (CoTR): A Novel Prompting Technique for Low Resource Languages","date":"2024-09-06","arxiv_id":"2409.04512","repositories_listed":0,"syntology":null},{"url":null,"slug":"building-math-agents-with-multi-turn","title":"Building Math Agents with Multi-Turn Iterative Preference Learning","date":"2024-09-04","arxiv_id":"2409.02392","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-and-automated","title":"Synthetic Data Generation and Automated Multidimensional Data Labeling for AI/ML in General and Circular Coordinates","date":"2024-09-03","arxiv_id":"2409.02079","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-synthetic-high","title":"Differentially Private Synthetic High-dimensional Tabular Stream","date":"2024-08-31","arxiv_id":"2409.00322","repositories_listed":0,"syntology":null},{"url":null,"slug":"smaller-weaker-yet-better-training-llm","title":"Smaller, Weaker, Yet Better: Training LLM Reasoners via Compute-Optimal Sampling","date":"2024-08-29","arxiv_id":"2408.16737","repositories_listed":0,"syntology":null},{"url":null,"slug":"are-pose-estimators-ready-for-the-open-world","title":"Are Pose Estimators Ready for the Open World? STAGE: Synthetic Data Generation Toolkit for Auditing 3D Human Pose Estimators","date":"2024-08-28","arxiv_id":"2408.16536","repositories_listed":0,"syntology":null},{"url":null,"slug":"lowclip-adapting-the-clip-model-architecture","title":"LowCLIP: Adapting the CLIP Model Architecture for Low-Resource Languages in Multimodal Image Retrieval Task","date":"2024-08-25","arxiv_id":"2408.13909","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-density-ratio-framework-for-evaluating-the","title":"A density ratio framework for evaluating the utility of synthetic data","date":"2024-08-23","arxiv_id":"2408.13167","repositories_listed":0,"syntology":null},{"url":null,"slug":"value-alignment-from-unstructured-text","title":"Value Alignment from Unstructured Text","date":"2024-08-19","arxiv_id":"2408.10392","repositories_listed":0,"syntology":null},{"url":null,"slug":"faster-private-minimum-spanning-trees","title":"Faster Private Minimum Spanning Trees","date":"2024-08-13","arxiv_id":"2408.06997","repositories_listed":0,"syntology":null},{"url":null,"slug":"nfdi4health-workflow-and-service-for","title":"NFDI4Health workflow and service for synthetic data generation, assessment and risk management","date":"2024-08-08","arxiv_id":"2408.04478","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-02927","title":"HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection","date":"2024-08-06","arxiv_id":"2408.02927","repositories_listed":0,"syntology":null},{"url":null,"slug":"winning-amazon-kdd-cup-24","title":"Winning Amazon KDD Cup'24","date":"2024-08-05","arxiv_id":"2408.04658","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00307","title":"ABC Align: Large Language Model Alignment for Safety & Accuracy","date":"2024-08-01","arxiv_id":"2408.00307","repositories_listed":0,"syntology":null},{"url":null,"slug":"2407-21476","title":"On the Problem of Text-To-Speech Model Selection for Synthetic Data Generation in Automatic Speech Recognition","date":"2024-07-31","arxiv_id":"2407.21476","repositories_listed":0,"syntology":null},{"url":null,"slug":"2408-00050","title":"Algorithms for Collaborative Machine Learning under Statistical Heterogeneity","date":"2024-07-31","arxiv_id":"2408.00050","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-effect-of-purely-synthetic-training","title":"On the Effect of Purely Synthetic Training Data for Different Automatic Speech Recognition Architectures","date":"2024-07-25","arxiv_id":"2407.17997","repositories_listed":0,"syntology":null},{"url":null,"slug":"genrec-a-flexible-data-generator-for","title":"Flexible Generation of Preference Data for Recommendation Analysis","date":"2024-07-23","arxiv_id":"2407.16594","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-reward-model-with-preference","title":"Boosting Reward Model with Preference-Conditional Multi-Aspect Synthetic Data Generation","date":"2024-07-22","arxiv_id":"2407.16008","repositories_listed":0,"syntology":null},{"url":null,"slug":"weak-to-strong-compositional-learning-from","title":"Weak-to-Strong Compositional Learning from Generative Models for Language-based Object Detection","date":"2024-07-21","arxiv_id":"2407.15296","repositories_listed":0,"syntology":null},{"url":null,"slug":"msct-addressing-time-varying-confounding-with","title":"MSCT: Addressing Time-Varying Confounding with Marginal Structural Causal Transformer for Counterfactual Post-Crash Traffic Prediction","date":"2024-07-19","arxiv_id":"2407.14065","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-and-interpretable-synthesizing","title":"Unsupervised and Interpretable Synthesizing for Electrical Time Series Based on Information Maximizing Generative Adversarial Nets","date":"2024-07-18","arxiv_id":"2407.13691","repositories_listed":0,"syntology":null},{"url":null,"slug":"llms-in-the-loop-part-1-expert-small-ai","title":"LLMs-in-the-loop Part-1: Expert Small AI Models for Bio-Medical Text Translation","date":"2024-07-16","arxiv_id":"2407.12126","repositories_listed":0,"syntology":null},{"url":null,"slug":"monocular-pose-estimation-of-articulated","title":"Monocular pose estimation of articulated surgical instruments in open surgery","date":"2024-07-16","arxiv_id":"2407.12138","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-cross-lingual-transfer-for","title":"Zero-shot Cross-Lingual Transfer for Synthetic Data Generation in Grammatical Error Detection","date":"2024-07-16","arxiv_id":"2407.11854","repositories_listed":0,"syntology":null},{"url":null,"slug":"what-makes-and-breaks-safety-fine-tuning","title":"What Makes and Breaks Safety Fine-tuning? A Mechanistic Study","date":"2024-07-14","arxiv_id":"2407.10264","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-for-discriminating","title":"Synthetic Data for Discriminating Serotonergic Neurons using Convolutional Neural Networks","date":"2024-07-08","arxiv_id":"2407.05701","repositories_listed":0,"syntology":null},{"url":null,"slug":"when-in-doubt-cascade-towards-building","title":"When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails","date":"2024-07-08","arxiv_id":"2407.06323","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-test-data-generation-using","title":"Synthetic Test Data Generation Using Recurrent Neural Networks: A Position Paper","date":"2024-07-07","arxiv_id":"2407.05410","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-models-for-tabular-data-imputation","title":"Diffusion Models for Tabular Data Imputation and Synthetic Data Generation","date":"2024-07-02","arxiv_id":"2407.02549","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-multimodal-question-generation","title":"Synthetic Multimodal Question Generation","date":"2024-07-02","arxiv_id":"2407.02233","repositories_listed":0,"syntology":null},{"url":null,"slug":"sk-vqa-synthetic-knowledge-generation-at","title":"SK-VQA: Synthetic Knowledge Generation at Scale for Training Context-Augmented Multimodal LLMs","date":"2024-06-28","arxiv_id":"2406.19593","repositories_listed":0,"syntology":null},{"url":null,"slug":"effects-of-using-synthetic-data-on-deep","title":"Effects of Using Synthetic Data on Deep Recommender Models' Performance","date":"2024-06-26","arxiv_id":"2406.18286","repositories_listed":0,"syntology":null},{"url":null,"slug":"principal-component-clustering-for-semantic","title":"Principal Component Clustering for Semantic Segmentation in Synthetic Data Generation","date":"2024-06-25","arxiv_id":"2406.17541","repositories_listed":0,"syntology":null},{"url":null,"slug":"tsynd-targeted-synthetic-data-generation-for","title":"TSynD: Targeted Synthetic Data Generation for Enhanced Medical Image Classification","date":"2024-06-25","arxiv_id":"2406.17473","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-retail-data-science-comprehensive","title":"Advancing Retail Data Science: Comprehensive Evaluation of Synthetic Data","date":"2024-06-19","arxiv_id":"2406.13130","repositories_listed":0,"syntology":null},{"url":null,"slug":"instruction-data-generation-and-unsupervised","title":"Instruction Data Generation and Unsupervised Adaptation for Speech Language Models","date":"2024-06-18","arxiv_id":"2406.12946","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatemg-synthetic-data-generation-to-control","title":"ChatEMG: Synthetic Data Generation to Control a Robotic Hand Orthosis for Stroke","date":"2024-06-17","arxiv_id":"2406.12123","repositories_listed":0,"syntology":null},{"url":null,"slug":"genmm-geometrically-and-temporally-consistent","title":"GenMM: Geometrically and Temporally Consistent Multimodal Data Generation for Video and LiDAR","date":"2024-06-15","arxiv_id":"2406.10722","repositories_listed":0,"syntology":null},{"url":null,"slug":"mallm-gan-multi-agent-large-language-model-as","title":"MALLM-GAN: Multi-Agent Large Language Model as Generative Adversarial Network for Synthesizing Tabular Data","date":"2024-06-15","arxiv_id":"2406.10521","repositories_listed":0,"syntology":null},{"url":"/paper/robopoint-a-vision-language-model-for-spatial","slug":"robopoint-a-vision-language-model-for-spatial","title":"RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Robotics","date":"2024-06-15","arxiv_id":"2406.10721","repositories_listed":0,"syntology":null},{"url":null,"slug":"benchmarking-generative-models-on","title":"Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming","date":"2024-06-14","arxiv_id":"2406.09891","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-llms-driven-synthetic-data-generation","title":"On LLMs-Driven Synthetic Data Generation, Curation, and Evaluation: A Survey","date":"2024-06-14","arxiv_id":"2406.15126","repositories_listed":0,"syntology":null},{"url":null,"slug":"simgen-simulator-conditioned-driving-scene","title":"SimGen: Simulator-conditioned Driving Scene Generation","date":"2024-06-13","arxiv_id":"2406.09386","repositories_listed":0,"syntology":null},{"url":null,"slug":"curating-grounded-synthetic-data-with-global","title":"Curating Grounded Synthetic Data with Global Perspectives for Equitable AI","date":"2024-06-10","arxiv_id":"2406.10258","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffinject-revisiting-debias-via-synthetic","title":"DiffInject: Revisiting Debias via Synthetic Data Generation using Diffusion-based Style Injection","date":"2024-06-10","arxiv_id":"2406.06134","repositories_listed":0,"syntology":null},{"url":null,"slug":"securenet-a-comparative-study-of-deberta-and","title":"SecureNet: A Comparative Study of DeBERTa and Large Language Models for Phishing Detection","date":"2024-06-10","arxiv_id":"2406.06663","repositories_listed":0,"syntology":null},{"url":null,"slug":"ctsyn-a-foundational-model-for-cross-tabular","title":"CTSyn: A Foundational Model for Cross Tabular Data Generation","date":"2024-06-07","arxiv_id":"2406.04619","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-indoor-temperature-forecasting","title":"Enhancing Indoor Temperature Forecasting through Synthetic Data in Low-Data Environments","date":"2024-06-07","arxiv_id":"2406.04890","repositories_listed":0,"syntology":null},{"url":null,"slug":"chatlang-8-an-llm-based-synthetic-data","title":"ChatLang-8: An LLM-Based Synthetic Data Generation Framework for Grammatical Error Correction","date":"2024-06-05","arxiv_id":"2406.03202","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-outliers-navigating-identity","title":"Synthetic Data Outliers: Navigating Identity Disclosure","date":"2024-06-04","arxiv_id":"2406.02736","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-clinical-documentation-with","title":"Enhancing Clinical Documentation with Synthetic Data: Leveraging Generative Models for Improved Accuracy","date":"2024-06-03","arxiv_id":"2406.06569","repositories_listed":0,"syntology":null},{"url":null,"slug":"genpalm-contactless-palmprint-generation-with","title":"GenPalm: Contactless Palmprint Generation with Diffusion Models","date":"2024-06-01","arxiv_id":"2406.00287","repositories_listed":0,"syntology":null},{"url":null,"slug":"masked-language-modeling-becomes-conditional","title":"Masked Language Modeling Becomes Conditional Density Estimation for Tabular Data Synthesis","date":"2024-05-31","arxiv_id":"2405.20602","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-open-source-large-language-models","title":"Leveraging Open-Source Large Language Models for encoding Social Determinants of Health using an Intelligent Router","date":"2024-05-30","arxiv_id":"2405.19631","repositories_listed":0,"syntology":null},{"url":null,"slug":"interpretable-classification-of-wiki-review","title":"Interpretable classification of wiki-review streams","date":"2024-05-28","arxiv_id":"2405.18335","repositories_listed":0,"syntology":null},{"url":null,"slug":"nv-embed-improved-techniques-for-training","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","date":"2024-05-27","arxiv_id":"2405.17428","repositories_listed":0,"syntology":null},{"url":null,"slug":"recent-advances-in-text-embedding-a","title":"Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark","date":"2024-05-27","arxiv_id":"2406.01607","repositories_listed":0,"syntology":null},{"url":"/paper/kinetgan-enabling-distributed-network","slug":"kinetgan-enabling-distributed-network","title":"KiNETGAN: Enabling Distributed Network Intrusion Detection through Knowledge-Infused Synthetic Data Generation","date":"2024-05-26","arxiv_id":"2405.16476","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-for-intersectional","title":"Synthetic Data Generation for Intersectional Fairness by Leveraging Hierarchical Group Structure","date":"2024-05-23","arxiv_id":"2405.14521","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-diverse-data-generation-for","title":"Diverse and Effective Synthetic Data Generation for Adaptable Zero-Shot Dialogue State Tracking","date":"2024-05-21","arxiv_id":"2405.12468","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-fnirs-neuroimaging-through","title":"Advancing fNIRS Neuroimaging through Synthetic Data Generation and Machine Learning Applications","date":"2024-05-18","arxiv_id":"2405.11242","repositories_listed":0,"syntology":null},{"url":null,"slug":"permissioned-blockchain-based-framework-for","title":"Permissioned Blockchain-based Framework for Ranking Synthetic Data Generators","date":"2024-05-12","arxiv_id":"2405.07196","repositories_listed":0,"syntology":null},{"url":null,"slug":"inference-with-combining-rules-from-multiple","title":"Inference With Combining Rules From Multiple Differentially Private Synthetic Datasets","date":"2024-05-08","arxiv_id":"2405.04769","repositories_listed":0,"syntology":null},{"url":null,"slug":"clustering-of-disease-trajectories-with","title":"Clustering of Disease Trajectories with Explainable Machine Learning: A Case Study on Postoperative Delirium Phenotypes","date":"2024-05-06","arxiv_id":"2405.03327","repositories_listed":0,"syntology":null},{"url":null,"slug":"domain-transferred-synthetic-data-generation","title":"Domain-Transferred Synthetic Data Generation for Improving Monocular Depth Estimation","date":"2024-05-02","arxiv_id":"2405.01113","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-metric-learning-based-out-of","title":"Deep Metric Learning-Based Out-of-Distribution Detection with Synthetic Outlier Exposure","date":"2024-05-01","arxiv_id":"2405.00631","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-statistical-data","title":"Privacy-Preserving Statistical Data Generation: Application to Sepsis Detection","date":"2024-04-25","arxiv_id":"2404.16638","repositories_listed":0,"syntology":null},{"url":"/paper/upose3d-uncertainty-aware-3d-human-pose","slug":"upose3d-uncertainty-aware-3d-human-pose","title":"UPose3D: Uncertainty-Aware 3D Human Pose Estimation with Cross-View and Temporal Cues","date":"2024-04-23","arxiv_id":"2404.14634","repositories_listed":0,"syntology":null}],"record_sha256":"0951c7818faca8fea7073e627dcf6eacb51eb7db13eb5632c8fd6d8bdf44b18b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}