{"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/5","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":5,"pages_in_order":9,"rows_per_page":100,"rows":[401,500],"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/4","next":"/task/synthetic-data-generation/papers/6","papers":[{"url":null,"slug":"assessing-generative-models-for-structured","title":"Assessing Generative Models for Structured Data","date":"2025-03-26","arxiv_id":"2503.20903","repositories_listed":0,"syntology":null},{"url":null,"slug":"small-object-detection-a-comprehensive-survey","title":"Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications","date":"2025-03-26","arxiv_id":"2503.20516","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-laws-of-synthetic-data-for-language","title":"Scaling Laws of Synthetic Data for Language Models","date":"2025-03-25","arxiv_id":"2503.19551","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuro-symbolic-scene-graph-conditioning-for","title":"Neuro-Symbolic Scene Graph Conditioning for Synthetic Image Dataset Generation","date":"2025-03-21","arxiv_id":"2503.17224","repositories_listed":0,"syntology":null},{"url":null,"slug":"project-jenkins-turning-monkey-neural-data","title":"Project Jenkins: Turning Monkey Neural Data into Robotic Arm Movement, and Back","date":"2025-03-19","arxiv_id":"2503.14847","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-using-large","title":"Synthetic Data Generation Using Large Language Models: Advances in Text and Code","date":"2025-03-18","arxiv_id":"2503.14023","repositories_listed":0,"syntology":null},{"url":null,"slug":"auggen-synthetic-augmentation-can-improve","title":"AugGen: Synthetic Augmentation Can Improve Discriminative Models","date":"2025-03-14","arxiv_id":"2503.11544","repositories_listed":0,"syntology":null},{"url":null,"slug":"cyclepose-leveraging-cycle-consistency-for","title":"CyclePose -- Leveraging Cycle-Consistency for Annotation-Free Nuclei Segmentation in Fluorescence Microscopy","date":"2025-03-14","arxiv_id":"2503.11266","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-learning-inspired-controlnet-guidance","title":"Active Learning Inspired ControlNet Guidance for Augmenting Semantic Segmentation Datasets","date":"2025-03-12","arxiv_id":"2503.09221","repositories_listed":0,"syntology":null},{"url":null,"slug":"local-look-ahead-guidance-via-verifier-in-the","title":"Local Look-Ahead Guidance via Verifier-in-the-Loop for Automated Theorem Proving","date":"2025-03-12","arxiv_id":"2503.09730","repositories_listed":0,"syntology":null},{"url":null,"slug":"plan-and-act-improving-planning-of-agents-for","title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","date":"2025-03-12","arxiv_id":"2503.09572","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-for-minimum","title":"Synthetic Data Generation for Minimum-Exposure Navigation in a Time-Varying Environment using Generative AI Models","date":"2025-03-09","arxiv_id":"2503.06619","repositories_listed":0,"syntology":null},{"url":null,"slug":"attention-based-synthetic-data-generation-for","title":"Attention-Based Synthetic Data Generation for Calibration-Enhanced Survival Analysis: A Case Study for Chronic Kidney Disease Using Electronic Health Records","date":"2025-03-08","arxiv_id":"2503.06096","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-consensus-privacy-metrics-framework-for","title":"A Consensus Privacy Metrics Framework for Synthetic Data","date":"2025-03-06","arxiv_id":"2503.04980","repositories_listed":0,"syntology":null},{"url":null,"slug":"cofindiff-controllable-financial-diffusion","title":"CoFinDiff: Controllable Financial Diffusion Model for Time Series Generation","date":"2025-03-06","arxiv_id":"2503.04164","repositories_listed":0,"syntology":null},{"url":null,"slug":"hilgen-hierarchically-informed-data","title":"HILGEN: Hierarchically-Informed Data Generation for Biomedical NER Using Knowledgebases and Large Language Models","date":"2025-03-06","arxiv_id":"2503.04930","repositories_listed":0,"syntology":null},{"url":null,"slug":"rethinking-synthetic-data-definitions-a","title":"Rethinking Synthetic Data definitions: A privacy driven approach","date":"2025-03-05","arxiv_id":"2503.03506","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-learning-of-diverse-code-edits","title":"Robust Learning of Diverse Code Edits","date":"2025-03-05","arxiv_id":"2503.03656","repositories_listed":0,"syntology":null},{"url":null,"slug":"spinml-customized-synthetic-data-generation","title":"SpinML: Customized Synthetic Data Generation for Private Training of Specialized ML Models","date":"2025-03-05","arxiv_id":"2503.03160","repositories_listed":0,"syntology":null},{"url":null,"slug":"oceansim-a-gpu-accelerated-underwater-robot","title":"OceanSim: A GPU-Accelerated Underwater Robot Perception Simulation Framework","date":"2025-03-03","arxiv_id":"2503.01074","repositories_listed":0,"syntology":null},{"url":"/paper/alleviating-distribution-shift-in-synthetic","slug":"alleviating-distribution-shift-in-synthetic","title":"Alleviating Distribution Shift in Synthetic Data for Machine Translation Quality Estimation","date":"2025-02-27","arxiv_id":"2502.19941","repositories_listed":0,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":11,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":11,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/alleviating-distribution-shift-in-synthetic#ran","syntology_url":"https://syntology.ai/paper/2502.19941","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.19941"}},"official":null}},{"url":null,"slug":"on-synthetic-data-strategies-for-domain","title":"On Synthetic Data Strategies for Domain-Specific Generative Retrieval","date":"2025-02-25","arxiv_id":"2502.17957","repositories_listed":0,"syntology":null},{"url":"/paper/fig-forward-inverse-generation-for-low","slug":"fig-forward-inverse-generation-for-low","title":"FIG: Forward-Inverse Generation for Low-Resource Domain-specific Event Detection","date":"2025-02-24","arxiv_id":"2502.17394","repositories_listed":0,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":2,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/fig-forward-inverse-generation-for-low#ran","syntology_url":"https://syntology.ai/paper/2502.17394","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.17394"}},"official":null}},{"url":null,"slug":"predicting-liquidity-aware-bond-yields-using","title":"Predicting Liquidity-Aware Bond Yields using Causal GANs and Deep Reinforcement Learning with LLM Evaluation","date":"2025-02-24","arxiv_id":"2502.17011","repositories_listed":0,"syntology":null},{"url":null,"slug":"rewardds-privacy-preserving-fine-tuning-for","title":"RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis","date":"2025-02-23","arxiv_id":"2502.18517","repositories_listed":0,"syntology":null},{"url":null,"slug":"mvip-a-dataset-and-methods-for-application","title":"MVIP -- A Dataset and Methods for Application Oriented Multi-View and Multi-Modal Industrial Part Recognition","date":"2025-02-21","arxiv_id":"2502.15448","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-canary-s-echo-auditing-privacy-risks-of","title":"The Canary's Echo: Auditing Privacy Risks of LLM-Generated Synthetic Text","date":"2025-02-19","arxiv_id":"2502.14921","repositories_listed":0,"syntology":null},{"url":null,"slug":"theorem-prover-as-a-judge-for-synthetic-data","title":"Theorem Prover as a Judge for Synthetic Data Generation","date":"2025-02-18","arxiv_id":"2502.13137","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-gaming-to-research-gta-v-for-synthetic","title":"From Gaming to Research: GTA V for Synthetic Data Generation for Robotics and Navigations","date":"2025-02-17","arxiv_id":"2502.12303","repositories_listed":0,"syntology":null},{"url":null,"slug":"shapelib-designing-a-library-of-procedural-3d","title":"ShapeLib: Designing a library of programmatic 3D shape abstractions with Large Language Models","date":"2025-02-13","arxiv_id":"2502.08884","repositories_listed":0,"syntology":null},{"url":null,"slug":"typhoon-t1-an-open-thai-reasoning-model","title":"Typhoon T1: An Open Thai Reasoning Model","date":"2025-02-13","arxiv_id":"2502.09042","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-distribution-prediction-a-unified","title":"Generative Distribution Prediction: A Unified Approach to Multimodal Learning","date":"2025-02-10","arxiv_id":"2502.07090","repositories_listed":0,"syntology":null},{"url":null,"slug":"is-api-access-to-llms-useful-for-generating","title":"Is API Access to LLMs Useful for Generating Private Synthetic Tabular Data?","date":"2025-02-10","arxiv_id":"2502.06555","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-and-ethical-insider-threat-detection","title":"Scalable and Ethical Insider Threat Detection through Data Synthesis and Analysis by LLMs","date":"2025-02-10","arxiv_id":"2502.07045","repositories_listed":0,"syntology":null},{"url":null,"slug":"multifloodsynth-multi-annotated-flood","title":"MultiFloodSynth: Multi-Annotated Flood Synthetic Dataset Generation","date":"2025-02-06","arxiv_id":"2502.03966","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-prompt-optimization-techniques","title":"Automatic Prompt Optimization Techniques: Exploring the Potential for Synthetic Data Generation","date":"2025-02-05","arxiv_id":"2502.03078","repositories_listed":0,"syntology":null},{"url":null,"slug":"gold-medalist-performance-in-solving-olympiad","title":"Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2","date":"2025-02-05","arxiv_id":"2502.03544","repositories_listed":0,"syntology":null},{"url":null,"slug":"bare-combining-base-and-instruction-tuned","title":"BARE: Leveraging Base Language Models for Few-Shot Synthetic Data Generation","date":"2025-02-03","arxiv_id":"2502.01697","repositories_listed":0,"syntology":null},{"url":null,"slug":"coddllm-empowering-large-language-models-for","title":"CoddLLM: Empowering Large Language Models for Data Analytics","date":"2025-02-01","arxiv_id":"2502.00329","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-for-augmenting","title":"Synthetic Data Generation for Augmenting Small Samples","date":"2025-01-30","arxiv_id":"2501.18741","repositories_listed":0,"syntology":null},{"url":null,"slug":"making-sense-of-data-in-the-wild-data","title":"Making Sense of Data in the Wild: Data Analysis Automation at Scale","date":"2025-01-27","arxiv_id":"2502.15718","repositories_listed":0,"syntology":null},{"url":null,"slug":"programming-by-examples-meets-historical","title":"Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction","date":"2025-01-27","arxiv_id":"2501.16524","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-data-augmentation-challenge-zero","title":"Generative Data Augmentation Challenge: Zero-Shot Speech Synthesis for Personalized Speech Enhancement","date":"2025-01-23","arxiv_id":"2501.13372","repositories_listed":0,"syntology":null},{"url":null,"slug":"embedding-driven-diversity-sampling-to","title":"Embedding-Driven Diversity Sampling to Improve Few-Shot Synthetic Data Generation","date":"2025-01-20","arxiv_id":"2501.11199","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-enrichment-opportunities-for","title":"Data Enrichment Opportunities for Distribution Grid Cable Networks using Variational Autoencoders","date":"2025-01-19","arxiv_id":"2501.10920","repositories_listed":0,"syntology":null},{"url":null,"slug":"sequential-patchcore-anomaly-detection-for","title":"Sequential PatchCore: Anomaly Detection for Surface Inspection using Synthetic Impurities","date":"2025-01-16","arxiv_id":"2501.09579","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-realistic-synthetic-head-rotation","title":"Generating Realistic Synthetic Head Rotation Data for Extended Reality using Deep Learning","date":"2025-01-15","arxiv_id":"2501.09050","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-system-2-reasoning-in-llms-learning","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Though","date":"2025-01-08","arxiv_id":"2501.04682","repositories_listed":0,"syntology":null},{"url":null,"slug":"user-simulation-in-the-era-of-generative-ai","title":"User Simulation in the Era of Generative AI: User Modeling, Synthetic Data Generation, and System Evaluation","date":"2025-01-08","arxiv_id":"2501.04410","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-the-understanding-of-fine-grained","title":"Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets","date":"2025-01-07","arxiv_id":"2501.03637","repositories_listed":0,"syntology":null},{"url":null,"slug":"reading-with-intent-neutralizing-intent","title":"Reading with Intent -- Neutralizing Intent","date":"2025-01-07","arxiv_id":"2501.03475","repositories_listed":0,"syntology":null},{"url":null,"slug":"license-plate-images-generation-with","title":"License Plate Images Generation with Diffusion Models","date":"2025-01-06","arxiv_id":"2501.03374","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-synthetic-data-be-fair-and-private-a","title":"Can Synthetic Data be Fair and Private? A Comparative Study of Synthetic Data Generation and Fairness Algorithms","date":"2025-01-03","arxiv_id":"2501.01785","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-series-language-model-for-descriptive","title":"Time Series Language Model for Descriptive Caption Generation","date":"2025-01-03","arxiv_id":"2501.01832","repositories_listed":0,"syntology":null},{"url":null,"slug":"safesynthdp-leveraging-large-language-models","title":"SafeSynthDP: Leveraging Large Language Models for Privacy-Preserving Synthetic Data Generation Using Differential Privacy","date":"2024-12-30","arxiv_id":"2412.20641","repositories_listed":0,"syntology":null},{"url":null,"slug":"targa-targeted-synthetic-data-generation-for","title":"TARGA: Targeted Synthetic Data Generation for Practical Reasoning over Structured Data","date":"2024-12-27","arxiv_id":"2412.19544","repositories_listed":0,"syntology":null},{"url":null,"slug":"mask-factory-towards-high-quality-synthetic","title":"Mask Factory: Towards High-quality Synthetic Data Generation for Dichotomous Image Segmentation","date":"2024-12-26","arxiv_id":"2412.19080","repositories_listed":0,"syntology":null},{"url":null,"slug":"htr-jand-handwritten-text-recognition-with","title":"HTR-JAND: Handwritten Text Recognition with Joint Attention Network and Knowledge Distillation","date":"2024-12-24","arxiv_id":"2412.18524","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-crack-detection-using-deep","title":"Autonomous Crack Detection using Deep Learning on Synthetic Thermogram Datasets","date":"2024-12-21","arxiv_id":"2412.16499","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-contrastive-learning-for-semantic","title":"Leveraging Contrastive Learning for Semantic Segmentation with Consistent Labels Across Varying Appearances","date":"2024-12-21","arxiv_id":"2412.16592","repositories_listed":0,"syntology":null},{"url":null,"slug":"differentially-private-federated-learning-of","title":"Differentially Private Federated Learning of Diffusion Models for Synthetic Tabular Data Generation","date":"2024-12-20","arxiv_id":"2412.16083","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-equity-in-health-modeling-with-gpt4","title":"Improving Equity in Health Modeling with GPT4-Turbo Generated Synthetic Data: A Comparative Study","date":"2024-12-20","arxiv_id":"2412.16335","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-systematic-examination-of-preference","title":"A Systematic Examination of Preference Learning through the Lens of Instruction-Following","date":"2024-12-18","arxiv_id":"2412.15282","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-throughput-digital-twin-framework-for","title":"High-throughput digital twin framework for predicting neurite deterioration using MetaFormer attention","date":"2024-12-18","arxiv_id":"2501.08334","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthcypher-a-fully-synthetic-data-generation","title":"Auto-Cypher: Improving LLMs on Cypher generation via LLM-supervised generation-verification framework","date":"2024-12-17","arxiv_id":"2412.12612","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-zoo","title":"Generative Zoo","date":"2024-12-11","arxiv_id":"2412.08101","repositories_listed":0,"syntology":null},{"url":null,"slug":"calico-conversational-agent-localization-via","title":"CALICO: Conversational Agent Localization via Synthetic Data Generation","date":"2024-12-06","arxiv_id":"2412.05388","repositories_listed":0,"syntology":null},{"url":null,"slug":"alma-alignment-with-minimal-annotation","title":"ALMA: Alignment with Minimal Annotation","date":"2024-12-05","arxiv_id":"2412.04305","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffupt-class-imbalance-mitigation-for","title":"DiffuPT: Class Imbalance Mitigation for Glaucoma Detection via Diffusion Based Generation and Model Pretraining","date":"2024-12-04","arxiv_id":"2412.03629","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-collaborative-synthetic-data","title":"End to End Collaborative Synthetic Data Generation","date":"2024-12-04","arxiv_id":"2412.03766","repositories_listed":0,"syntology":null},{"url":null,"slug":"surveying-the-effects-of-quality-diversity","title":"Surveying the Effects of Quality, Diversity, and Complexity in Synthetic Data From Large Language Models","date":"2024-12-04","arxiv_id":"2412.02980","repositories_listed":0,"syntology":null},{"url":null,"slug":"energy-based-modelling-for-discrete-and-mixed","title":"Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces","date":"2024-12-02","arxiv_id":"2412.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"malt-improving-reasoning-with-multi-agent-llm","title":"MALT: Improving Reasoning with Multi-Agent LLM Training","date":"2024-12-02","arxiv_id":"2412.01928","repositories_listed":0,"syntology":null},{"url":null,"slug":"needle-a-generative-ai-powered-monte-carlo","title":"Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries","date":"2024-12-01","arxiv_id":"2412.00639","repositories_listed":0,"syntology":null},{"url":null,"slug":"well-log-data-generation-and-imputation-using","title":"Well log data generation and imputation using sequence-based generative adversarial networks","date":"2024-12-01","arxiv_id":"2412.00718","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-lidar-editing-with-controllable","title":"LiDAR-EDIT: LiDAR Data Generation by Editing the Object Layouts in Real-World Scenes","date":"2024-11-30","arxiv_id":"2412.00592","repositories_listed":0,"syntology":null},{"url":null,"slug":"mag-v-a-multi-agent-framework-for-synthetic","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","date":"2024-11-28","arxiv_id":"2412.04494","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-document-ai-data-generation-through","title":"Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts","date":"2024-11-27","arxiv_id":"2412.03590","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-with-llm-for","title":"Synthetic Data Generation with LLM for Improved Depression Prediction","date":"2024-11-26","arxiv_id":"2411.17672","repositories_listed":0,"syntology":null},{"url":null,"slug":"anysynth-harnessing-the-power-of-image","title":"AnySynth: Harnessing the Power of Image Synthetic Data Generation for Generalized Vision-Language Tasks","date":"2024-11-24","arxiv_id":"2411.16749","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-data-scarcity-a-frequency-driven","title":"Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting","date":"2024-11-24","arxiv_id":"2411.15743","repositories_listed":0,"syntology":null},{"url":"/paper/high-precision-medical-speech-recognition","slug":"high-precision-medical-speech-recognition","title":"High-precision medical speech recognition through synthetic data and semantic correction: UNITED-MEDASR","date":"2024-11-24","arxiv_id":"2412.00055","repositories_listed":0,"syntology":null},{"url":null,"slug":"llm-for-barcodes-generating-diverse-synthetic","title":"LLM for Barcodes: Generating Diverse Synthetic Data for Identity Documents","date":"2024-11-22","arxiv_id":"2411.14962","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-a-framework-on-tabular-synthetic-data","title":"Towards a framework on tabular synthetic data generation: a minimalist approach: theory, use cases, and limitations","date":"2024-11-17","arxiv_id":"2411.10982","repositories_listed":0,"syntology":null},{"url":null,"slug":"watermarking-generative-categorical-data","title":"Watermarking Generative Categorical Data","date":"2024-11-16","arxiv_id":"2411.10898","repositories_listed":0,"syntology":null},{"url":null,"slug":"generation-of-synthetic-gait-data-application","title":"Generation of synthetic gait data: application to multiple sclerosis patients' gait patterns","date":"2024-11-15","arxiv_id":"2411.10377","repositories_listed":0,"syntology":null},{"url":null,"slug":"hierarchical-conditional-tabular-gan-for","title":"Hierarchical Conditional Tabular GAN for Multi-Tabular Synthetic Data Generation","date":"2024-11-11","arxiv_id":"2411.07009","repositories_listed":0,"syntology":null},{"url":null,"slug":"maximizing-domain-generalization-in-fetal","title":"DRIFTS: Optimizing Domain Randomization with Synthetic Data and Weight Interpolation for Fetal Brain Tissue Segmentation","date":"2024-11-11","arxiv_id":"2411.06842","repositories_listed":0,"syntology":null},{"url":null,"slug":"differential-privacy-under-class-imbalance","title":"Differential Privacy Under Class Imbalance: Methods and Empirical Insights","date":"2024-11-08","arxiv_id":"2411.05733","repositories_listed":0,"syntology":null},{"url":null,"slug":"difflm-controllable-synthetic-data-generation","title":"DiffLM: Controllable Synthetic Data Generation via Diffusion Language Models","date":"2024-11-05","arxiv_id":"2411.03250","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancing-table-representations-with-llm","title":"Enhancing Table Representations with LLM-powered Synthetic Data Generation","date":"2024-11-04","arxiv_id":"2411.03356","repositories_listed":0,"syntology":null},{"url":null,"slug":"retrieval-enriched-zero-shot-image","title":"Retrieval-enriched zero-shot image classification in low-resource domains","date":"2024-11-01","arxiv_id":"2411.00988","repositories_listed":0,"syntology":null},{"url":null,"slug":"scalable-ai-framework-for-defect-detection-in","title":"Scalable AI Framework for Defect Detection in Metal Additive Manufacturing","date":"2024-11-01","arxiv_id":"2411.00960","repositories_listed":0,"syntology":null},{"url":null,"slug":"clinical-evaluation-of-medical-image","title":"Clinical Evaluation of Medical Image Synthesis: A Case Study in Wireless Capsule Endoscopy","date":"2024-10-31","arxiv_id":"2411.00178","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-synthetic-faces-how-synthetic","title":"Unveiling Synthetic Faces: How Synthetic Datasets Can Expose Real Identities","date":"2024-10-31","arxiv_id":"2410.24015","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-utility-in-synthetic-banking","title":"Evaluating utility in synthetic banking microdata applications","date":"2024-10-29","arxiv_id":"2410.22519","repositories_listed":0,"syntology":null},{"url":null,"slug":"soccerguard-investigating-injury-risk-factors","title":"SoccerGuard: Investigating Injury Risk Factors for Professional Soccer Players with Machine Learning","date":"2024-10-29","arxiv_id":"2411.08901","repositories_listed":0,"syntology":null},{"url":null,"slug":"unpicking-data-at-the-seams-vaes","title":"Unpicking Data at the Seams: VAEs, Disentanglement and Independent Components","date":"2024-10-29","arxiv_id":"2410.22559","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-benchmarks-in-medical","title":"Large Language Model Benchmarks in Medical Tasks","date":"2024-10-28","arxiv_id":"2410.21348","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetica-large-scale-synthetic-data-for","title":"Synthetica: Large Scale Synthetic Data for Robot Perception","date":"2024-10-28","arxiv_id":"2410.21153","repositories_listed":0,"syntology":null}],"record_sha256":"5be821dc7ab16857088f3ab7182b8b8e9b127258fdb9f7f4fc6f81b2a4337976","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}