{"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/4","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":4,"pages_in_order":9,"rows_per_page":100,"rows":[301,400],"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/3","next":"/task/synthetic-data-generation/papers/5","papers":[{"url":"/paper/tabular-transformers-for-modeling","slug":"tabular-transformers-for-modeling","title":"Tabular Transformers for Modeling Multivariate Time Series","date":"2020-11-03","arxiv_id":"2011.01843","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 2 unverified","sample_list":"/paper/tabular-transformers-for-modeling#ran","syntology_url":"https://syntology.ai/paper/2011.01843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2011.01843"}},"official":{"repos":["IBM/TabFormer"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":[]}}},{"url":"/paper/end-to-end-synthetic-data-generation-for","slug":"end-to-end-synthetic-data-generation-for","title":"End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems","date":"2020-10-12","arxiv_id":"2010.06028","repositories_listed":1,"syntology":null},{"url":"/paper/synthesising-clinically-realistic-chest-x","slug":"synthesising-clinically-realistic-chest-x","title":"Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs","date":"2020-10-07","arxiv_id":"2010.03975","repositories_listed":1,"syntology":null},{"url":"/paper/sync-a-copula-based-framework-for-generating","slug":"sync-a-copula-based-framework-for-generating","title":"SYNC: A Copula based Framework for Generating Synthetic Data from Aggregated Sources","date":"2020-09-20","arxiv_id":"2009.09471","repositories_listed":1,"syntology":null},{"url":"/paper/groove2groove-one-shot-music-style-transfer","slug":"groove2groove-one-shot-music-style-transfer","title":"Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data","date":"2020-08-26","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/partially-synthetic-data-for-recommender","slug":"partially-synthetic-data-for-recommender","title":"Partially Synthetic Data for Recommender Systems: Prediction Performance and Preference Hiding","date":"2020-08-09","arxiv_id":"2008.03797","repositories_listed":1,"syntology":null},{"url":"/paper/hide-and-seek-privacy-challenge","slug":"hide-and-seek-privacy-challenge","title":"Hide-and-Seek Privacy Challenge","date":"2020-07-23","arxiv_id":"2007.12087","repositories_listed":1,"syntology":null},{"url":"/paper/deltapy-a-framework-for-tabular-data","slug":"deltapy-a-framework-for-tabular-data","title":"DeltaPy: A Framework for Tabular Data Augmentation in Python","date":"2020-05-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/unnatural-language-processing-bridging-the","slug":"unnatural-language-processing-bridging-the","title":"Unnatural Language Processing: Bridging the Gap Between Synthetic and Natural Language Data","date":"2020-04-28","arxiv_id":"2004.13645","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-mean-embeddings-with","slug":"differentially-private-mean-embeddings-with","title":"DP-MERF: Differentially Private Mean Embeddings with Random Features for Practical Privacy-Preserving Data Generation","date":"2020-02-26","arxiv_id":"2002.11603","repositories_listed":1,"syntology":{"n":3,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/differentially-private-mean-embeddings-with#ran","syntology_url":"https://syntology.ai/paper/2002.11603","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.11603"}},"official":{"repos":["ParkLabML/DP-MERF"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/segmenting-unseen-industrial-components-in-a","slug":"segmenting-unseen-industrial-components-in-a","title":"Segmenting Unseen Industrial Components in a Heavy Clutter Using RGB-D Fusion and Synthetic Data","date":"2020-02-10","arxiv_id":"2002.03501","repositories_listed":1,"syntology":null},{"url":"/paper/cor-gan-correlation-capturing-convolutional","slug":"cor-gan-correlation-capturing-convolutional","title":"CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare Records","date":"2020-01-25","arxiv_id":"2001.09346","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-mixed-type-data-1","slug":"differentially-private-mixed-type-data-1","title":"Differentially Private Synthetic Mixed-Type Data Generation For Unsupervised Learning","date":"2019-12-06","arxiv_id":"1912.03250","repositories_listed":1,"syntology":{"n":11,"n_ran":11,"n_constructed":0,"n_ran_checked":9,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/differentially-private-mixed-type-data-1#ran","syntology_url":"https://syntology.ai/paper/1912.03250","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1912.03250"}},"official":{"repos":["DPautoGAN/DPautoGAN"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/comparative-study-of-differentially-private","slug":"comparative-study-of-differentially-private","title":"Comparative Study of Differentially Private Synthetic Data Algorithms from the NIST PSCR Differential Privacy Synthetic Data Challenge","date":"2019-11-28","arxiv_id":"1911.12704","repositories_listed":1,"syntology":null},{"url":"/paper/using-u-nets-to-create-high-fidelity-virtual","slug":"using-u-nets-to-create-high-fidelity-virtual","title":"Using U-Nets to Create High-Fidelity Virtual Observations of the Solar Corona","date":"2019-11-10","arxiv_id":"1911.04006","repositories_listed":1,"syntology":null},{"url":"/paper/data-generation-for-neural-programming-by","slug":"data-generation-for-neural-programming-by","title":"Data Generation for Neural Programming by Example","date":"2019-11-06","arxiv_id":"1911.02624","repositories_listed":1,"syntology":null},{"url":"/paper/animal-detection-in-man-made-environments","slug":"animal-detection-in-man-made-environments","title":"Animal Detection in Man-made Environments","date":"2019-10-24","arxiv_id":"1910.11443","repositories_listed":1,"syntology":null},{"url":"/paper/differentially-private-mixed-type-data","slug":"differentially-private-mixed-type-data","title":"Differentially Private Mixed-Type Data Generation For Unsupervised Learning","date":"2019-09-25","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/supervised-symbolic-music-style-translation","slug":"supervised-symbolic-music-style-translation","title":"Supervised Symbolic Music Style Translation Using Synthetic Data","date":"2019-07-04","arxiv_id":"1907.02265","repositories_listed":1,"syntology":null},{"url":"/paper/pate-gan-generating-synthetic-data-with","slug":"pate-gan-generating-synthetic-data-with","title":"PATE-GAN: Generating Synthetic Data with Differential Privacy Guarantees","date":"2019-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-generate-synthetic-data-via","slug":"learning-to-generate-synthetic-data-via","title":"Learning to Generate Synthetic Data via Compositing","date":"2019-04-10","arxiv_id":"1904.05475","repositories_listed":1,"syntology":null},{"url":"/paper/domain-randomization-for-scene-specific-car","slug":"domain-randomization-for-scene-specific-car","title":"Domain Randomization for Scene-Specific Car Detection and Pose Estimation","date":"2018-11-14","arxiv_id":"1811.05939","repositories_listed":1,"syntology":null},{"url":"/paper/synthetically-trained-icon-proposals-for","slug":"synthetically-trained-icon-proposals-for","title":"Synthetically Trained Icon Proposals for Parsing and Summarizing Infographics","date":"2018-07-27","arxiv_id":"1807.10441","repositories_listed":1,"syntology":null},{"url":"/paper/a-generic-deep-architecture-for-single-image","slug":"a-generic-deep-architecture-for-single-image","title":"A Generic Deep Architecture for Single Image Reflection Removal and Image Smoothing","date":"2017-08-11","arxiv_id":"1708.03474","repositories_listed":1,"syntology":null},{"url":"/paper/a-self-supervised-learning-system-for-object","slug":"a-self-supervised-learning-system-for-object","title":"A Self-supervised Learning System for Object Detection using Physics Simulation and Multi-view Pose Estimation","date":"2017-03-09","arxiv_id":"1703.03347","repositories_listed":1,"syntology":null},{"url":null,"slug":"lightweight-safety-guardrails-via-synthetic","title":"Lightweight Safety Guardrails via Synthetic Data and RL-guided Adversarial Training","date":"2025-07-11","arxiv_id":"2507.08284","repositories_listed":0,"syntology":null},{"url":null,"slug":"docie-xllm25-in-context-learning-for","title":"DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations","date":"2025-07-08","arxiv_id":"2507.05997","repositories_listed":0,"syntology":null},{"url":null,"slug":"sok-can-synthetic-images-replace-real-data-a","title":"SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation","date":"2025-06-24","arxiv_id":"2506.19360","repositories_listed":0,"syntology":null},{"url":null,"slug":"pucktrick-a-library-for-making-synthetic-data","title":"PuckTrick: A Library for Making Synthetic Data More Realistic","date":"2025-06-23","arxiv_id":"2506.18499","repositories_listed":0,"syntology":null},{"url":null,"slug":"robomonkey-scaling-test-time-sampling-and","title":"RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models","date":"2025-06-21","arxiv_id":"2506.17811","repositories_listed":0,"syntology":null},{"url":null,"slug":"latent-noise-injection-for-private-and","title":"Latent Noise Injection for Private and Statistically Aligned Synthetic Data Generation","date":"2025-06-19","arxiv_id":"2506.16636","repositories_listed":0,"syntology":null},{"url":null,"slug":"graph-convolutional-beta-vae-for-synthetic","title":"Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation","date":"2025-06-16","arxiv_id":"2506.13628","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-synthetic-mirror-synthetic-data-at-the","title":"The Synthetic Mirror -- Synthetic Data at the Age of Agentic AI","date":"2025-06-15","arxiv_id":"2506.13818","repositories_listed":0,"syntology":null},{"url":null,"slug":"2506-08312","title":"Private Evolution Converges","date":"2025-06-10","arxiv_id":"2506.08312","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatiotemporal-deep-learning-models-for","title":"Spatiotemporal deep learning models for detection of rapid intensification in cyclones","date":"2025-06-10","arxiv_id":"2506.08397","repositories_listed":0,"syntology":null},{"url":null,"slug":"unlocking-the-potential-of-large-language-2","title":"Unlocking the Potential of Large Language Models in the Nuclear Industry with Synthetic Data","date":"2025-06-10","arxiv_id":"2506.08750","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-human-activity-recognition-a","title":"Scaling Human Activity Recognition: A Comparative Evaluation of Synthetic Data Generation and Augmentation Techniques","date":"2025-06-09","arxiv_id":"2506.07612","repositories_listed":0,"syntology":null},{"url":null,"slug":"sop-bench-complex-industrial-sops-for","title":"SOP-Bench: Complex Industrial SOPs for Evaluating LLM Agents","date":"2025-06-09","arxiv_id":"2506.08119","repositories_listed":0,"syntology":null},{"url":null,"slug":"sparq-synthetic-problem-generation-for","title":"SPARQ: Synthetic Problem Generation for Reasoning via Quality-Diversity Algorithms","date":"2025-06-06","arxiv_id":"2506.06499","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-tabular-data-methods-attacks-and","title":"Synthetic Tabular Data: Methods, Attacks and Defenses","date":"2025-06-06","arxiv_id":"2506.06108","repositories_listed":0,"syntology":null},{"url":null,"slug":"gen-n-val-agentic-image-data-generation-and","title":"Gen-n-Val: Agentic Image Data Generation and Validation","date":"2025-06-05","arxiv_id":"2506.04676","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-dataset-generation-for-autonomous","title":"Synthetic Dataset Generation for Autonomous Mobile Robots Using 3D Gaussian Splatting for Vision Training","date":"2025-06-05","arxiv_id":"2506.05092","repositories_listed":0,"syntology":null},{"url":null,"slug":"beyond-the-norm-a-survey-of-synthetic-data","title":"Beyond the Norm: A Survey of Synthetic Data Generation for Rare Events","date":"2025-06-04","arxiv_id":"2506.06380","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-prompt-design-impact-quality-of-data","title":"Does Prompt Design Impact Quality of Data Imputation by LLMs?","date":"2025-06-04","arxiv_id":"2506.04172","repositories_listed":0,"syntology":null},{"url":null,"slug":"corrigibility-as-a-singular-target-a-vision","title":"Corrigibility as a Singular Target: A Vision for Inherently Reliable Foundation Models","date":"2025-06-03","arxiv_id":"2506.03056","repositories_listed":0,"syntology":null},{"url":null,"slug":"ip-dialog-evaluating-implicit-personalization","title":"IP-Dialog: Evaluating Implicit Personalization in Dialogue Systems with Synthetic Data","date":"2025-06-03","arxiv_id":"2506.02449","repositories_listed":0,"syntology":null},{"url":null,"slug":"refedit-a-benchmark-and-method-for-improving","title":"RefEdit: A Benchmark and Method for Improving Instruction-based Image Editing Model on Referring Expressions","date":"2025-06-03","arxiv_id":"2506.03448","repositories_listed":0,"syntology":null},{"url":null,"slug":"smote-dp-improving-privacy-utility-tradeoff","title":"SMOTE-DP: Improving Privacy-Utility Tradeoff with Synthetic Data","date":"2025-06-02","arxiv_id":"2506.01907","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-domain-absa-conversation-dataset","title":"Multi-Domain ABSA Conversation Dataset Generation via LLMs for Real-World Evaluation and Model Comparison","date":"2025-05-30","arxiv_id":"2505.24701","repositories_listed":0,"syntology":null},{"url":null,"slug":"vietmix-a-naturally-occurring-vietnamese","title":"VietMix: A Naturally Occurring Vietnamese-English Code-Mixed Corpus with Iterative Augmentation for Machine Translation","date":"2025-05-30","arxiv_id":"2505.24472","repositories_listed":0,"syntology":null},{"url":null,"slug":"cryoccd-conditional-cycle-consistent","title":"CryoCCD: Conditional Cycle-consistent Diffusion with Biophysical Modeling for Cryo-EM Synthesis","date":"2025-05-29","arxiv_id":"2505.23444","repositories_listed":0,"syntology":null},{"url":null,"slug":"stresstest-can-your-speech-lm-handle-the","title":"StressTest: Can YOUR Speech LM Handle the Stress?","date":"2025-05-28","arxiv_id":"2505.22765","repositories_listed":0,"syntology":null},{"url":null,"slug":"phir-hera-fairy-an-english-fairytaler-is-a","title":"Phir Hera Fairy: An English Fairytaler is a Strong Faker of Fluent Speech in Low-Resource Indian Languages","date":"2025-05-27","arxiv_id":"2505.20693","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-solution-to-video-fusion-from-multi","title":"A Unified Solution to Video Fusion: From Multi-Frame Learning to Benchmarking","date":"2025-05-26","arxiv_id":"2505.19858","repositories_listed":0,"syntology":null},{"url":null,"slug":"from-alignment-to-advancement-bootstrapping","title":"From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data","date":"2025-05-26","arxiv_id":"2505.20166","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-heart-rejection-detection-in-xpci","title":"Improving Heart Rejection Detection in XPCI Images Using Synthetic Data Augmentation","date":"2025-05-26","arxiv_id":"2505.19746","repositories_listed":0,"syntology":null},{"url":null,"slug":"mosaic-data-free-knowledge-distillation-via","title":"Mosaic: Data-Free Knowledge Distillation via Mixture-of-Experts for Heterogeneous Distributed Environments","date":"2025-05-26","arxiv_id":"2505.19699","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-is-not-all-you-need-examining-llms","title":"Reasoning Is Not All You Need: Examining LLMs for Multi-Turn Mental Health Conversations","date":"2025-05-26","arxiv_id":"2505.20201","repositories_listed":0,"syntology":null},{"url":null,"slug":"sipdo-closed-loop-prompt-optimization-via","title":"SIPDO: Closed-Loop Prompt Optimization via Synthetic Data Feedback","date":"2025-05-26","arxiv_id":"2505.19514","repositories_listed":0,"syntology":null},{"url":null,"slug":"pigpvae-physics-informed-gaussian-process","title":"PIGPVAE: Physics-Informed Gaussian Process Variational Autoencoders","date":"2025-05-25","arxiv_id":"2505.19320","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-prompt-is-mightier-than-the-example","title":"The Prompt is Mightier than the Example","date":"2025-05-24","arxiv_id":"2505.18485","repositories_listed":0,"syntology":null},{"url":null,"slug":"large-language-model-as-user-daily-behavior","title":"Large language model as user daily behavior data generator: balancing population diversity and individual personality","date":"2025-05-23","arxiv_id":"2505.17615","repositories_listed":0,"syntology":null},{"url":null,"slug":"data-driven-breakthroughs-and-future","title":"Data-Driven Breakthroughs and Future Directions in AI Infrastructure: A Comprehensive Review","date":"2025-05-22","arxiv_id":"2505.16771","repositories_listed":0,"syntology":null},{"url":null,"slug":"aug2search-enhancing-facebook-marketplace","title":"Aug2Search: Enhancing Facebook Marketplace Search with LLM-Generated Synthetic Data Augmentation","date":"2025-05-21","arxiv_id":"2505.16065","repositories_listed":0,"syntology":null},{"url":null,"slug":"forging-time-series-with-language-a-large","title":"Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation","date":"2025-05-21","arxiv_id":"2505.17103","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-limitations-in-the-synthetic","title":"Challenges and Limitations in the Synthetic Generation of mHealth Sensor Data","date":"2025-05-20","arxiv_id":"2505.14206","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-low-resource-mt-via-synthetic-data","title":"Scaling Low-Resource MT via Synthetic Data Generation with LLMs","date":"2025-05-20","arxiv_id":"2505.14423","repositories_listed":0,"syntology":null},{"url":null,"slug":"routenator-a-router-based-multi-modal","title":"RouteNator: A Router-Based Multi-Modal Architecture for Generating Synthetic Training Data for Function Calling LLMs","date":"2025-05-15","arxiv_id":"2505.10495","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-federated-learning-with-confidence","title":"Robust Federated Learning with Confidence-Weighted Filtering and GAN-Based Completion under Noisy and Incomplete Data","date":"2025-05-14","arxiv_id":"2505.09733","repositories_listed":0,"syntology":null},{"url":null,"slug":"privacy-preserving-analytics-for-smart-meter","title":"Privacy-Preserving Analytics for Smart Meter (AMI) Data: A Hybrid Approach to Comply with CPUC Privacy Regulations","date":"2025-05-13","arxiv_id":"2505.08237","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-code-surgery-repairing-bugs-and","title":"Synthetic Code Surgery: Repairing Bugs and Vulnerabilities with LLMs and Synthetic Data","date":"2025-05-12","arxiv_id":"2505.07372","repositories_listed":0,"syntology":null},{"url":null,"slug":"uni-aims-ai-powered-microscopy-image-analysis","title":"Uni-AIMS: AI-Powered Microscopy Image Analysis","date":"2025-05-11","arxiv_id":"2505.06918","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-reliable-synthetic-clinical-trial","title":"Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints","date":"2025-05-08","arxiv_id":"2505.05019","repositories_listed":0,"syntology":null},{"url":null,"slug":"ai-generated-fall-data-assessing-llms-and","title":"AI-Generated Fall Data: Assessing LLMs and Diffusion Model for Wearable Fall Detection","date":"2025-05-07","arxiv_id":"2505.04660","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-omics-based-classification-the-role","title":"Improving Omics-Based Classification: The Role of Feature Selection and Synthetic Data Generation","date":"2025-05-06","arxiv_id":"2505.03387","repositories_listed":0,"syntology":null},{"url":null,"slug":"modeling-supply-chain-compliance-response","title":"Modeling supply chain compliance response strategies based on AI synthetic data with structural path regression: A Simulation Study of EU 2027 Mandatory Labor Regulations","date":"2025-05-04","arxiv_id":"2505.06261","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthesize-on-graph-knowledgeable-synthetic","title":"Synthesize-on-Graph: Knowledgeable Synthetic Data Generation for Continue Pre-training of Large Language Models","date":"2025-05-02","arxiv_id":"2505.00979","repositories_listed":0,"syntology":null},{"url":null,"slug":"artificial-intelligence-for-personalized","title":"Artificial Intelligence for Personalized Prediction of Alzheimer's Disease Progression: A Survey of Methods, Data Challenges, and Future Directions","date":"2025-04-29","arxiv_id":"2504.21189","repositories_listed":0,"syntology":null},{"url":null,"slug":"unified-multi-task-learning-model-fusion-for","title":"Unified Multi-Task Learning & Model Fusion for Efficient Language Model Guardrailing","date":"2025-04-27","arxiv_id":"2504.19333","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimizing-the-privacy-utility-balance-using","title":"Optimizing the Privacy-Utility Balance using Synthetic Data and Configurable Perturbation Pipelines","date":"2025-04-24","arxiv_id":"2504.18596","repositories_listed":0,"syntology":null},{"url":null,"slug":"tardiff-target-oriented-diffusion-guidance","title":"TarDiff: Target-Oriented Diffusion Guidance for Synthetic Electronic Health Record Time Series Generation","date":"2025-04-24","arxiv_id":"2504.17613","repositories_listed":0,"syntology":null},{"url":"/paper/case-study-fine-tuning-small-language-models","slug":"case-study-fine-tuning-small-language-models","title":"Case Study: Fine-tuning Small Language Models for Accurate and Private CWE Detection in Python Code","date":"2025-04-23","arxiv_id":"2504.16584","repositories_listed":0,"syntology":null},{"url":null,"slug":"clarifycoder-clarification-aware-fine-tuning","title":"ClarifyCoder: Clarification-Aware Fine-Tuning for Programmatic Problem Solving","date":"2025-04-23","arxiv_id":"2504.16331","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-from-reasoning-failures-via","title":"Learning from Reasoning Failures via Synthetic Data Generation","date":"2025-04-20","arxiv_id":"2504.14523","repositories_listed":0,"syntology":null},{"url":null,"slug":"metasynth-meta-prompting-driven-agentic","title":"MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation","date":"2025-04-17","arxiv_id":"2504.12563","repositories_listed":0,"syntology":null},{"url":null,"slug":"scaling-instruction-tuned-llms-to-million","title":"Scaling Instruction-Tuned LLMs to Million-Token Contexts via Hierarchical Synthetic Data Generation","date":"2025-04-17","arxiv_id":"2504.12637","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-diversity-and-quality-of-llm","title":"Evaluating the Diversity and Quality of LLM Generated Content","date":"2025-04-16","arxiv_id":"2504.12522","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-for-blood-vessel-network","title":"Synthetic Data for Blood Vessel Network Extraction","date":"2025-04-16","arxiv_id":"2504.11858","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-vertical-public-private-split-for","title":"Leveraging Vertical Public-Private Split for Improved Synthetic Data Generation","date":"2025-04-15","arxiv_id":"2504.10987","repositories_listed":0,"syntology":null},{"url":null,"slug":"safe-construct-redefining-construction-safety","title":"Safe-Construct: Redefining Construction Safety Violation Recognition as 3D Multi-View Engagement Task","date":"2025-04-15","arxiv_id":"2504.10880","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthfm-training-modality-agnostic-foundation","title":"SynthFM: Training Modality-agnostic Foundation Models for Medical Image Segmentation without Real Medical Data","date":"2025-04-11","arxiv_id":"2504.08177","repositories_listed":0,"syntology":null},{"url":null,"slug":"monoplace3d-learning-3d-aware-object","title":"MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection","date":"2025-04-09","arxiv_id":"2504.06801","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-self-supervised-framework-for-space-object","title":"A Self-Supervised Framework for Space Object Behaviour Characterisation","date":"2025-04-08","arxiv_id":"2504.06176","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-data-generation-multi-step-rl-for","title":"Synthetic Data Generation & Multi-Step RL for Reasoning & Tool Use","date":"2025-04-07","arxiv_id":"2504.04736","repositories_listed":0,"syntology":null},{"url":null,"slug":"cortex-avd-a-framework-for-corner-case","title":"CORTEX-AVD: A Framework for CORner Case Testing and EXploration in Autonomous Vehicle Development","date":"2025-04-04","arxiv_id":"2504.03989","repositories_listed":0,"syntology":null},{"url":null,"slug":"advancing-semantic-caching-for-llms-with","title":"Advancing Semantic Caching for LLMs with Domain-Specific Embeddings and Synthetic Data","date":"2025-04-03","arxiv_id":"2504.02268","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-linguistic-divide-a-survey-on","title":"Bridging the Linguistic Divide: A Survey on Leveraging Large Language Models for Machine Translation","date":"2025-04-02","arxiv_id":"2504.01919","repositories_listed":0,"syntology":null},{"url":null,"slug":"tamis-tailored-membership-inference-attacks","title":"TAMIS: Tailored Membership Inference Attacks on Synthetic Data","date":"2025-04-01","arxiv_id":"2504.00758","repositories_listed":0,"syntology":null},{"url":null,"slug":"synthetic-news-generation-for-fake-news","title":"Synthetic News Generation for Fake News Classification","date":"2025-03-31","arxiv_id":"2503.24206","repositories_listed":0,"syntology":null},{"url":null,"slug":"xl-instruct-synthetic-data-for-cross-lingual","title":"XL-Instruct: Synthetic Data for Cross-Lingual Open-Ended Generation","date":"2025-03-29","arxiv_id":"2503.22973","repositories_listed":0,"syntology":null}],"record_sha256":"7a4e77da6ed68746e37f768a466dbfe6611a33c7214f8ac04aa57d1ee6f6c255","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}