{"url":"/task/dataset-generation","name":"Dataset Generation","slug":"dataset-generation","description_markdown":"The task involves enhancing the training of target application (e.g. autonomous driving systems) by generating datasets of diverse and critical elements (e.g. traffic scenarios). Traditional methods rely on expensive and limited datasets, which often fail to capture rare but essential situations that can pose risks during testing.","categories":[{"name":"Robots","url":"/area/robots"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":308,"papers_with_code":144,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":144,"tagged_in_all":308,"items":[{"url":"/paper/rethinking-table-parsing-using-graph-neural","title":"Rethinking Table Recognition using Graph Neural Networks","date":"2019-05-31","arxiv_id":"1905.13391","repositories_listed":5,"syntology":null},{"url":"/paper/segmenting-unknown-3d-objects-from-real-depth","title":"Segmenting Unknown 3D Objects from Real Depth Images using Mask R-CNN Trained on Synthetic Data","date":"2018-09-16","arxiv_id":"1809.05825","repositories_listed":4,"syntology":null},{"url":"/paper/cephalo-multi-modal-vision-language-models","title":"Cephalo: Multi-Modal Vision-Language Models for Bio-Inspired Materials Analysis and Design","date":"2024-05-29","arxiv_id":"2405.19076","repositories_listed":3,"syntology":null},{"url":"/paper/masked-face-dataset-generation-and-masked","title":"Masked Face Dataset Generation and Masked Face Recognition","date":"2023-11-13","arxiv_id":"2311.07475","repositories_listed":3,"syntology":null},{"url":"/paper/learning-based-nlos-detection-and-uncertainty","title":"Learning-based NLOS Detection and Uncertainty Prediction of GNSS Observations with Transformer-Enhanced LSTM Network","date":"2023-09-01","arxiv_id":"2309.00480","repositories_listed":3,"syntology":null},{"url":"/paper/scrape-cut-paste-and-learn-automated-dataset","title":"Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics","date":"2022-10-18","arxiv_id":"2210.09814","repositories_listed":3,"syntology":null},{"url":"/paper/zerogen-efficient-zero-shot-learning-via","title":"ZeroGen: Efficient Zero-shot Learning via Dataset Generation","date":"2022-02-16","arxiv_id":"2202.07922","repositories_listed":3,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":7}},{"url":"/paper/real-time-per-garment-virtual-try-on-with","title":"Real-Time Per-Garment Virtual Try-On with Temporal Consistency for Loose-Fitting Garments","date":"2025-06-14","arxiv_id":"2506.12348","repositories_listed":2,"syntology":null},{"url":"/paper/an-adaptive-open-source-dataset-generation","title":"OpenLS-DGF: An Adaptive Open-Source Dataset Generation Framework for Machine Learning Tasks in Logic Synthesis","date":"2024-11-14","arxiv_id":"2411.09422","repositories_listed":2,"syntology":null},{"url":"/paper/padetbench-towards-benchmarking-physical","title":"PADetBench: Towards Benchmarking Physical Attacks against Object Detection","date":"2024-08-17","arxiv_id":"2408.09181","repositories_listed":2,"syntology":null},{"url":"/paper/datadream-few-shot-guided-dataset-generation","title":"DataDream: Few-shot Guided Dataset Generation","date":"2024-07-15","arxiv_id":"2407.10910","repositories_listed":2,"syntology":{"n":21,"n_ran":17,"n_unverified":4,"n_pointer_only":21}},{"url":"/paper/semantically-rich-local-dataset-generation","title":"Semantically Rich Local Dataset Generation for Explainable AI in Genomics","date":"2024-07-03","arxiv_id":"2407.02984","repositories_listed":2,"syntology":null},{"url":"/paper/forcing-diffuse-distributions-out-of-language","title":"Forcing Diffuse Distributions out of Language Models","date":"2024-04-16","arxiv_id":"2404.10859","repositories_listed":2,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/learning-to-compute-grobner-bases","title":"Learning to Compute Gröbner Bases","date":"2023-11-21","arxiv_id":"2311.12904","repositories_listed":2,"syntology":{"n":18,"n_ran":12,"n_unverified":6,"n_pointer_only":17}},{"url":"/paper/developing-a-scalable-benchmark-for-assessing","title":"Developing a Scalable Benchmark for Assessing Large Language Models in Knowledge Graph Engineering","date":"2023-08-31","arxiv_id":"2308.16622","repositories_listed":2,"syntology":null},{"url":"/paper/progen-progressive-zero-shot-dataset","title":"ProGen: Progressive Zero-shot Dataset Generation via In-context Feedback","date":"2022-10-22","arxiv_id":"2210.12329","repositories_listed":2,"syntology":null},{"url":"/paper/semantic-segmentation-for-autonomous-driving","title":"Semantic Segmentation for Autonomous Driving: Model Evaluation, Dataset Generation, Perspective Comparison, and Real-Time Capability","date":"2022-07-26","arxiv_id":"2207.12939","repositories_listed":2,"syntology":null},{"url":"/paper/smart-home-appliances-chat-with-your-fridge","title":"Smart Home Appliances: Chat with Your Fridge","date":"2019-12-19","arxiv_id":"1912.09589","repositories_listed":2,"syntology":null},{"url":"/paper/affordance-learning-for-end-to-end-visuomotor","title":"Affordance Learning for End-to-End Visuomotor Robot Control","date":"2019-03-10","arxiv_id":"1903.04053","repositories_listed":2,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/vision-language-action-models-in-robotic","title":"Vision Language Action Models in Robotic Manipulation: A Systematic Review","date":"2025-07-14","arxiv_id":"2507.10672","repositories_listed":1,"syntology":null},{"url":"/paper/communicating-smartly-in-the-molecular-domain","title":"Communicating Smartly in the Molecular Domain: Neural Networks in the Internet of Bio-Nano Things","date":"2025-06-25","arxiv_id":"2506.20589","repositories_listed":1,"syntology":null},{"url":"/paper/enhancing-clinical-models-with-pseudo-data","title":"Enhancing Clinical Models with Pseudo Data for De-identification","date":"2025-06-15","arxiv_id":"2506.12674","repositories_listed":1,"syntology":null},{"url":"/paper/code-execution-as-grounded-supervision-for","title":"Code Execution as Grounded Supervision for LLM Reasoning","date":"2025-06-12","arxiv_id":"2506.10343","repositories_listed":1,"syntology":null},{"url":"/paper/hierarchical-lexical-graph-for-enhanced-multi","title":"Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval","date":"2025-06-09","arxiv_id":"2506.08074","repositories_listed":1,"syntology":null},{"url":"/paper/morse-500-a-programmatically-controllable","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","date":"2025-06-05","arxiv_id":"2506.05523","repositories_listed":1,"syntology":null},{"url":"/paper/timegraph-synthetic-benchmark-datasets-for","title":"TimeGraph: Synthetic Benchmark Datasets for Robust Time-Series Causal Discovery","date":"2025-06-02","arxiv_id":"2506.01361","repositories_listed":1,"syntology":null},{"url":"/paper/track-anything-annotate-video-annotation-and","title":"Track Anything Annotate: Video annotation and dataset generation of computer vision models","date":"2025-05-23","arxiv_id":"2505.17884","repositories_listed":1,"syntology":null},{"url":"/paper/f-ancgan-an-attention-enhanced-cycle","title":"F-ANcGAN: An Attention-Enhanced Cycle Consistent Generative Adversarial Architecture for Synthetic Image Generation of Nanoparticles","date":"2025-05-23","arxiv_id":"2505.18106","repositories_listed":1,"syntology":null},{"url":"/paper/seg-3d-by-pc2d-multi-view-projection-for","title":"seg_3D_by_PC2D: Multi-View Projection for Domain Generalization and Adaptation in 3D Semantic Segmentation","date":"2025-05-21","arxiv_id":"2505.15545","repositories_listed":1,"syntology":null},{"url":"/paper/tiny-qa-benchmark-ultra-lightweight-synthetic","title":"Tiny QA Benchmark++: Ultra-Lightweight, Synthetic Multilingual Dataset Generation & Smoke-Tests for Continuous LLM Evaluation","date":"2025-05-17","arxiv_id":"2505.12058","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}