{"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/dataset-generation/papers/2","list_of":"/task/dataset-generation","task":"Dataset 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":2,"pages_in_order":4,"rows_per_page":100,"rows":[101,200],"of":308,"counts":{"archive_papers_tagged":308,"with_a_code_link":144,"where_syntology_ran_a_sample":30,"not_listed_spam_title":0,"listed":308,"listed_where_code_ran":30,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":25,"every_run_a_failure_of_syntologys_instrument":5,"listed_with_a_run_with_no_instrument_failure":25,"listed_every_run_a_failure_of_syntologys_instrument":5,"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/dataset-generation","prev":"/task/dataset-generation","next":"/task/dataset-generation/papers/3","papers":[{"url":"/paper/jabberwock-a-tool-for-webassembly-dataset","slug":"jabberwock-a-tool-for-webassembly-dataset","title":"JABBERWOCK: A Tool for WebAssembly Dataset Generation and Its Application to Malicious Website Detection","date":"2023-06-09","arxiv_id":"2306.05698","repositories_listed":1,"syntology":null},{"url":"/paper/neurograph-benchmarks-for-graph-machine","slug":"neurograph-benchmarks-for-graph-machine","title":"NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics","date":"2023-06-09","arxiv_id":"2306.06202","repositories_listed":1,"syntology":{"n":4,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 3 unverified","sample_list":"/paper/neurograph-benchmarks-for-graph-machine#ran","syntology_url":"https://syntology.ai/paper/2306.06202","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.06202"}},"official":{"repos":["anwar-said/neurograph"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"url":"/paper/graphcleaner-detecting-mislabelled-samples-in","slug":"graphcleaner-detecting-mislabelled-samples-in","title":"GraphCleaner: Detecting Mislabelled Samples in Popular Graph Learning Benchmarks","date":"2023-05-30","arxiv_id":"2306.00015","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 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; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/graphcleaner-detecting-mislabelled-samples-in#ran","syntology_url":"https://syntology.ai/paper/2306.00015","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00015"}},"official":{"repos":["lywww/graphcleaner"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sim-suction-learning-a-suction-grasp-policy","slug":"sim-suction-learning-a-suction-grasp-policy","title":"Sim-Suction: Learning a Suction Grasp Policy for Cluttered Environments Using a Synthetic Benchmark","date":"2023-05-25","arxiv_id":"2305.16378","repositories_listed":1,"syntology":null},{"url":"/paper/goat-fine-tuned-llama-outperforms-gpt-4-on","slug":"goat-fine-tuned-llama-outperforms-gpt-4-on","title":"Goat: Fine-tuned LLaMA Outperforms GPT-4 on Arithmetic Tasks","date":"2023-05-23","arxiv_id":"2305.14201","repositories_listed":1,"syntology":null},{"url":"/paper/sim-mees-modular-end-effector-system-grasping","slug":"sim-mees-modular-end-effector-system-grasping","title":"Sim-MEES: Modular End-Effector System Grasping Dataset for Mobile Manipulators in Cluttered Environments","date":"2023-05-17","arxiv_id":"2305.10580","repositories_listed":1,"syntology":null},{"url":"/paper/zero-shot-racially-balanced-dataset","slug":"zero-shot-racially-balanced-dataset","title":"Zero-shot racially balanced dataset generation using an existing biased StyleGAN2","date":"2023-05-12","arxiv_id":"2305.07710","repositories_listed":1,"syntology":null},{"url":"/paper/paxqa-generating-cross-lingual-question","slug":"paxqa-generating-cross-lingual-question","title":"PAXQA: Generating Cross-lingual Question Answering Examples at Training Scale","date":"2023-04-24","arxiv_id":"2304.12206","repositories_listed":1,"syntology":null},{"url":"/paper/dcface-synthetic-face-generation-with-dual","slug":"dcface-synthetic-face-generation-with-dual","title":"DCFace: Synthetic Face Generation with Dual Condition Diffusion Model","date":"2023-04-14","arxiv_id":"2304.07060","repositories_listed":1,"syntology":null},{"url":"/paper/camdiff-camouflage-image-augmentation-via","slug":"camdiff-camouflage-image-augmentation-via","title":"CamDiff: Camouflage Image Augmentation via Diffusion Model","date":"2023-04-11","arxiv_id":"2304.05469","repositories_listed":1,"syntology":null},{"url":"/paper/simbaml-connecting-mechanistic-models-and","slug":"simbaml-connecting-mechanistic-models-and","title":"SimbaML: Connecting Mechanistic Models and Machine Learning with Augmented Data","date":"2023-04-08","arxiv_id":"2304.04000","repositories_listed":1,"syntology":null},{"url":"/paper/liquid-a-framework-for-list-question","slug":"liquid-a-framework-for-list-question","title":"LIQUID: A Framework for List Question Answering Dataset Generation","date":"2023-02-03","arxiv_id":"2302.01691","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"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) · 0 unverified","sample_list":"/paper/liquid-a-framework-for-list-question#ran","syntology_url":"https://syntology.ai/paper/2302.01691","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.01691"}},"official":{"repos":["dmis-lab/liquid"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-realistic-underwater-dataset","slug":"towards-realistic-underwater-dataset","title":"Towards Realistic Underwater Dataset Generation and Color Restoration","date":"2022-11-27","arxiv_id":"2211.14821","repositories_listed":1,"syntology":null},{"url":"/paper/a-framework-for-large-scale-synthetic-graph","slug":"a-framework-for-large-scale-synthetic-graph","title":"A Framework for Large Scale Synthetic Graph Dataset Generation","date":"2022-10-04","arxiv_id":"2210.01944","repositories_listed":1,"syntology":null},{"url":"/paper/realflow-em-based-realistic-optical-flow","slug":"realflow-em-based-realistic-optical-flow","title":"RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos","date":"2022-07-22","arxiv_id":"2207.11075","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-dataset-generation-for-adversarial","slug":"synthetic-dataset-generation-for-adversarial","title":"Synthetic Dataset Generation for Adversarial Machine Learning Research","date":"2022-07-21","arxiv_id":"2207.10719","repositories_listed":1,"syntology":null},{"url":"/paper/hm3d-abo-a-photo-realistic-dataset-for-object","slug":"hm3d-abo-a-photo-realistic-dataset-for-object","title":"HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction","date":"2022-06-24","arxiv_id":"2206.12356","repositories_listed":1,"syntology":null},{"url":"/paper/a-universal-synthetic-dataset-for-machine","slug":"a-universal-synthetic-dataset-for-machine","title":"A universal synthetic dataset for machine learning on spectroscopic data","date":"2022-06-13","arxiv_id":"2206.06031","repositories_listed":1,"syntology":null},{"url":"/paper/bias-reduction-via-cooperative-bargaining-in","slug":"bias-reduction-via-cooperative-bargaining-in","title":"Bias Reduction via Cooperative Bargaining in Synthetic Graph Dataset Generation","date":"2022-05-27","arxiv_id":"2205.13901","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-answer-visual-questions-from-web","slug":"learning-to-answer-visual-questions-from-web","title":"Learning to Answer Visual Questions from Web Videos","date":"2022-05-10","arxiv_id":"2205.05019","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/learning-to-answer-visual-questions-from-web#ran","syntology_url":"https://syntology.ai/paper/2205.05019","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2205.05019"}},"official":{"repos":["antoyang/just-ask"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/closing-the-loop-a-framework-for-trustworthy","slug":"closing-the-loop-a-framework-for-trustworthy","title":"Closing the Loop: A Framework for Trustworthy Machine Learning in Power Systems","date":"2022-03-14","arxiv_id":"2203.07505","repositories_listed":1,"syntology":{"n":11,"n_ran":10,"n_constructed":0,"n_ran_checked":10,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":10,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/closing-the-loop-a-framework-for-trustworthy#ran","syntology_url":"https://syntology.ai/paper/2203.07505","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.07505"}},"official":{"repos":["jbesty/irep_2022_closing_the_loop"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/a-semi-synthetic-dataset-generation-framework","slug":"a-semi-synthetic-dataset-generation-framework","title":"A Semi-Synthetic Dataset Generation Framework for Causal Inference in Recommender Systems","date":"2022-02-23","arxiv_id":"2202.11351","repositories_listed":1,"syntology":null},{"url":"/paper/adg-pose-automated-dataset-generation-for","slug":"adg-pose-automated-dataset-generation-for","title":"ADG-Pose: Automated Dataset Generation for Real-World Human Pose Estimation","date":"2022-02-01","arxiv_id":"2202.00753","repositories_listed":1,"syntology":null},{"url":"/paper/a-python-package-to-detect-anti-vaccine-users","slug":"a-python-package-to-detect-anti-vaccine-users","title":"Detecting Anti-Vaccine Users on Twitter","date":"2021-10-21","arxiv_id":"2110.11333","repositories_listed":1,"syntology":null},{"url":"/paper/synpick-a-dataset-for-dynamic-bin-picking","slug":"synpick-a-dataset-for-dynamic-bin-picking","title":"SynPick: A Dataset for Dynamic Bin Picking Scene Understanding","date":"2021-07-10","arxiv_id":"2107.04852","repositories_listed":1,"syntology":null},{"url":"/paper/sofamyroom-a-fast-and-multiplatform-shoebox","slug":"sofamyroom-a-fast-and-multiplatform-shoebox","title":"SofaMyRoom: a fast and multiplatform \"shoebox\" room simulator for binaural room impulse response dataset generation","date":"2021-06-24","arxiv_id":"2106.12992","repositories_listed":1,"syntology":null},{"url":"/paper/improving-paraphrase-detection-with-the","slug":"improving-paraphrase-detection-with-the","title":"Improving Paraphrase Detection with the Adversarial Paraphrasing Task","date":"2021-06-14","arxiv_id":"2106.07691","repositories_listed":1,"syntology":null},{"url":"/paper/perceptual-loss-for-robust-unsupervised","slug":"perceptual-loss-for-robust-unsupervised","title":"Perceptual Loss for Robust Unsupervised Homography Estimation","date":"2021-04-20","arxiv_id":"2104.10011","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"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) · 0 unverified","sample_list":"/paper/perceptual-loss-for-robust-unsupervised#ran","syntology_url":"https://syntology.ai/paper/2104.10011","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.10011"}},"official":{"repos":["NeurAI-Lab/biHomE"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/racklay-multi-layer-layout-estimation-for","slug":"racklay-multi-layer-layout-estimation-for","title":"Monocular Multi-Layer Layout Estimation for Warehouse Racks","date":"2021-03-16","arxiv_id":"2103.09174","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-dataset-generation-of-driver","slug":"synthetic-dataset-generation-of-driver","title":"Synthetic Dataset Generation of Driver Telematics","date":"2021-01-30","arxiv_id":"2102.00252","repositories_listed":1,"syntology":null},{"url":"/paper/mk-squit-synthesizing-questions-using","slug":"mk-squit-synthesizing-questions-using","title":"MK-SQuIT: Synthesizing Questions using Iterative Template-filling","date":"2020-11-04","arxiv_id":"2011.02566","repositories_listed":1,"syntology":null},{"url":"/paper/actionet-an-interactive-end-to-end-platform","slug":"actionet-an-interactive-end-to-end-platform","title":"Actionet: An Interactive End-To-End Platform For Task-Based Data Collection And Augmentation In 3D Environment","date":"2020-10-03","arxiv_id":"2010.01357","repositories_listed":1,"syntology":null},{"url":"/paper/afro-mnist-synthetic-generation-of-mnist","slug":"afro-mnist-synthetic-generation-of-mnist","title":"Afro-MNIST: Synthetic generation of MNIST-style datasets for low-resource languages","date":"2020-09-28","arxiv_id":"2009.13509","repositories_listed":1,"syntology":null},{"url":"/paper/image-generation-for-efficient-neural-network","slug":"image-generation-for-efficient-neural-network","title":"Image Generation for Efficient Neural Network Training in Autonomous Drone Racing","date":"2020-08-06","arxiv_id":"2008.02596","repositories_listed":1,"syntology":null},{"url":"/paper/learning-camera-miscalibration-detection","slug":"learning-camera-miscalibration-detection","title":"Learning Camera Miscalibration Detection","date":"2020-05-24","arxiv_id":"2005.11711","repositories_listed":1,"syntology":null},{"url":"/paper/private-dataset-generation-using-privacy","slug":"private-dataset-generation-using-privacy","title":"Private Dataset Generation Using Privacy Preserving Collaborative Learning","date":"2020-04-28","arxiv_id":"2004.13598","repositories_listed":1,"syntology":null},{"url":"/paper/viwi-vision-aided-mmwave-beam-tracking","slug":"viwi-vision-aided-mmwave-beam-tracking","title":"ViWi Vision-Aided mmWave Beam Tracking: Dataset, Task, and Baseline Solutions","date":"2020-02-06","arxiv_id":"2002.02445","repositories_listed":1,"syntology":null},{"url":"/paper/face-manifold-manifold-learning-for-synthetic","slug":"face-manifold-manifold-learning-for-synthetic","title":"Face Manifold: Manifold Learning for Synthetic Face Generation","date":"2019-10-03","arxiv_id":"1910.01403","repositories_listed":1,"syntology":null},{"url":"/paper/synthetic-dataset-generation-for-object-to","slug":"synthetic-dataset-generation-for-object-to","title":"Synthetic dataset generation for object-to-model deep learning in industrial applications","date":"2019-09-24","arxiv_id":"1909.10976","repositories_listed":1,"syntology":null},{"url":"/paper/learning-to-propagate-for-graph-meta-learning","slug":"learning-to-propagate-for-graph-meta-learning","title":"Learning to Propagate for Graph Meta-Learning","date":"2019-09-11","arxiv_id":"1909.05024","repositories_listed":1,"syntology":null},{"url":"/paper/gan-leaks-a-taxonomy-of-membership-inference","slug":"gan-leaks-a-taxonomy-of-membership-inference","title":"GAN-Leaks: A Taxonomy of Membership Inference Attacks against Generative Models","date":"2019-09-09","arxiv_id":"1909.03935","repositories_listed":1,"syntology":{"n":22,"n_ran":13,"n_constructed":0,"n_ran_checked":10,"n_instrument":3,"n_unverified":9,"n_honours":3,"n_violates":0,"n_no_contract":7,"n_pointer_only":5,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified","sample_list":"/paper/gan-leaks-a-taxonomy-of-membership-inference#ran","syntology_url":"https://syntology.ai/paper/1909.03935","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.03935"}},"official":{"repos":["DingfanChen/GAN-Leaks"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":10,"n_unverified":9,"ran_from_kinds":["official"]}}},{"url":"/paper/190513546","slug":"190513546","title":"LeagueAI: Improving object detector performance and flexibility through automatically generated training data and domain randomization","date":"2019-05-28","arxiv_id":"1905.13546","repositories_listed":1,"syntology":null},{"url":"/paper/190508633","slug":"190508633","title":"Fonts-2-Handwriting: A Seed-Augment-Train framework for universal digit classification","date":"2019-05-16","arxiv_id":"1905.08633","repositories_listed":1,"syntology":null},{"url":"/paper/building-large-machine-reading-comprehension","slug":"building-large-machine-reading-comprehension","title":"Building Large Machine Reading-Comprehension Datasets using Paragraph Vectors","date":"2016-12-13","arxiv_id":"1612.04342","repositories_listed":1,"syntology":null},{"url":null,"slug":"from-general-to-targeted-rewards-surpassing","title":"From General to Targeted Rewards: Surpassing GPT-4 in Open-Ended Long-Context Generation","date":"2025-06-19","arxiv_id":"2506.16024","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-large-scale-physically-based-synthetic","title":"A large-scale, physically-based synthetic dataset for satellite pose estimation","date":"2025-06-15","arxiv_id":"2506.12782","repositories_listed":0,"syntology":null},{"url":null,"slug":"generating-synthetic-stereo-datasets-using-3d","title":"Generating Synthetic Stereo Datasets using 3D Gaussian Splatting and Expert Knowledge Transfer","date":"2025-06-05","arxiv_id":"2506.04908","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":"cetbench-a-novel-dataset-constructed-via","title":"CETBench: A Novel Dataset constructed via Transformations over Programs for Benchmarking LLMs for Code-Equivalence Checking","date":"2025-06-04","arxiv_id":"2506.04019","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":"robo2vlm-visual-question-answering-from-large","title":"Robo2VLM: Visual Question Answering from Large-Scale In-the-Wild Robot Manipulation Datasets","date":"2025-05-21","arxiv_id":"2505.15517","repositories_listed":0,"syntology":null},{"url":null,"slug":"automatic-dataset-generation-for-knowledge","title":"Automatic Dataset Generation for Knowledge Intensive Question Answering Tasks","date":"2025-05-20","arxiv_id":"2505.14212","repositories_listed":0,"syntology":null},{"url":null,"slug":"fmsd-tts-few-shot-multi-speaker-multi-dialect","title":"FMSD-TTS: Few-shot Multi-Speaker Multi-Dialect Text-to-Speech Synthesis for Ü-Tsang, Amdo and Kham Speech Dataset Generation","date":"2025-05-20","arxiv_id":"2505.14351","repositories_listed":0,"syntology":null},{"url":null,"slug":"contextual-paralinguistic-data-creation-for","title":"Contextual Paralinguistic Data Creation for Multi-Modal Speech-LLM: Data Condensation and Spoken QA Generation","date":"2025-05-19","arxiv_id":"2505.13338","repositories_listed":0,"syntology":null},{"url":null,"slug":"event-based-star-tracking-under-spacecraft","title":"Event-based Star Tracking under Spacecraft Jitter: the e-STURT Dataset","date":"2025-05-19","arxiv_id":"2505.12588","repositories_listed":0,"syntology":null},{"url":"/paper/scalable-video-to-dataset-generation-for","slug":"scalable-video-to-dataset-generation-for","title":"Scalable Video-to-Dataset Generation for Cross-Platform Mobile Agents","date":"2025-05-19","arxiv_id":"2505.12632","repositories_listed":0,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/scalable-video-to-dataset-generation-for#ran","syntology_url":"https://syntology.ai/paper/2505.12632","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.12632"}},"official":null}},{"url":null,"slug":"guidance-for-intra-cardiac-echocardiography","title":"Guidance for Intra-cardiac Echocardiography Manipulation to Maintain Continuous Therapy Device Tip Visibility","date":"2025-05-08","arxiv_id":"2505.05518","repositories_listed":0,"syntology":null},{"url":null,"slug":"estimating-commonsense-scene-composition-on","title":"Estimating Commonsense Scene Composition on Belief Scene Graphs","date":"2025-05-05","arxiv_id":"2505.02405","repositories_listed":0,"syntology":null},{"url":null,"slug":"document-retrieval-augmented-fine-tuning","title":"Document Retrieval Augmented Fine-Tuning (DRAFT) for safety-critical software assessments","date":"2025-05-02","arxiv_id":"2505.01307","repositories_listed":0,"syntology":null},{"url":null,"slug":"v-2-r-bench-holistically-evaluating-lvlm","title":"V$^2$R-Bench: Holistically Evaluating LVLM Robustness to Fundamental Visual Variations","date":"2025-04-23","arxiv_id":"2504.16727","repositories_listed":0,"syntology":null},{"url":null,"slug":"mirrorverse-pushing-diffusion-models-to","title":"MirrorVerse: Pushing Diffusion Models to Realistically Reflect the World","date":"2025-04-21","arxiv_id":"2504.15397","repositories_listed":0,"syntology":null},{"url":null,"slug":"unreal-robotics-lab-a-high-fidelity-robotics","title":"Unreal Robotics Lab: A High-Fidelity Robotics Simulator with Advanced Physics and Rendering","date":"2025-04-19","arxiv_id":"2504.14135","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepwheel-generating-a-3d-synthetic-wheel","title":"DeepWheel: Generating a 3D Synthetic Wheel Dataset for Design and Performance Evaluation","date":"2025-04-15","arxiv_id":"2504.11347","repositories_listed":0,"syntology":null},{"url":null,"slug":"reasoning-inconsistencies-and-how-to-mitigate","title":"Reasoning Inconsistencies and How to Mitigate Them in Deep Learning","date":"2025-04-03","arxiv_id":"2504.02577","repositories_listed":0,"syntology":null},{"url":null,"slug":"concept-aware-lora-for-domain-aligned","title":"Concept-Aware LoRA for Domain-Aligned Segmentation Dataset Generation","date":"2025-03-28","arxiv_id":"2503.22172","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":"unveiling-the-invisible-reasoning-complex-1","title":"Unveiling the Invisible: Reasoning Complex Occlusions Amodally with AURA","date":"2025-03-13","arxiv_id":"2503.10225","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynamic-kgqa-a-scalable-framework-for","title":"Dynamic-KGQA: A Scalable Framework for Generating Adaptive Question Answering Datasets","date":"2025-03-06","arxiv_id":"2503.05049","repositories_listed":0,"syntology":null},{"url":null,"slug":"valuepilot-a-two-phase-framework-for-value","title":"ValuePilot: A Two-Phase Framework for Value-Driven Decision-Making","date":"2025-03-06","arxiv_id":"2503.04569","repositories_listed":0,"syntology":null},{"url":null,"slug":"technical-report-of-a-dmd-based","title":"Technical report of a DMD-based Characterization Method for Vision Sensors","date":"2025-03-04","arxiv_id":"2503.03781","repositories_listed":0,"syntology":null},{"url":null,"slug":"undertrained-image-reconstruction-for","title":"Undertrained Image Reconstruction for Realistic Degradation in Blind Image Super-Resolution","date":"2025-03-04","arxiv_id":"2503.02767","repositories_listed":0,"syntology":null},{"url":null,"slug":"webfaq-a-multilingual-collection-of-natural-q","title":"WebFAQ: A Multilingual Collection of Natural Q&A Datasets for Dense Retrieval","date":"2025-02-28","arxiv_id":"2502.20936","repositories_listed":0,"syntology":null},{"url":null,"slug":"holistic-audit-dataset-generation-for-llm","title":"Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal","date":"2025-02-26","arxiv_id":"2502.18810","repositories_listed":0,"syntology":null},{"url":null,"slug":"specdm-hyperspectral-dataset-synthesis-with","title":"SpecDM: Hyperspectral Dataset Synthesis with Pixel-level Semantic Annotations","date":"2025-02-24","arxiv_id":"2502.17056","repositories_listed":0,"syntology":null},{"url":null,"slug":"one-shot-federated-learning-with-classifier-1","title":"One-Shot Federated Learning with Classifier-Free Diffusion Models","date":"2025-02-12","arxiv_id":"2502.08488","repositories_listed":0,"syntology":null},{"url":null,"slug":"behavioral-entropy-guided-dataset-generation","title":"Behavioral Entropy-Guided Dataset Generation for Offline Reinforcement Learning","date":"2025-02-06","arxiv_id":"2502.04141","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":"synthetic-user-behavior-sequence-generation","title":"Synthetic User Behavior Sequence Generation with Large Language Models for Smart Homes","date":"2025-01-31","arxiv_id":"2501.19298","repositories_listed":0,"syntology":null},{"url":null,"slug":"itri-qa-a-toolset-for-customized-question","title":"iTRI-QA: a Toolset for Customized Question-Answer Dataset Generation Using Language Models for Enhanced Scientific Research","date":"2025-01-27","arxiv_id":"2502.15721","repositories_listed":0,"syntology":null},{"url":null,"slug":"measuring-and-mitigating-hallucinations-in","title":"Measuring and Mitigating Hallucinations in Vision-Language Dataset Generation for Remote Sensing","date":"2025-01-24","arxiv_id":"2501.14905","repositories_listed":0,"syntology":null},{"url":null,"slug":"unveiling-provider-bias-in-large-language","title":"The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation","date":"2025-01-14","arxiv_id":"2501.07849","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-error-covariance-estimation-for","title":"Neural Error Covariance Estimation for Precise LiDAR Localization","date":"2025-01-05","arxiv_id":"2501.02558","repositories_listed":0,"syntology":null},{"url":null,"slug":"dynscene-scalable-generation-of-dynamic","title":"DynScene: Scalable Generation of Dynamic Robotic Manipulation Scenes for Embodied AI","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"low-biased-general-annotated-dataset","title":"Low-Biased General Annotated Dataset Generation","date":"2025-01-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"movie2story-a-framework-for-understanding","title":"Movie2Story: A framework for understanding videos and telling stories in the form of novel text","date":"2024-12-19","arxiv_id":"2412.14965","repositories_listed":0,"syntology":null},{"url":null,"slug":"unbiased-general-annotated-dataset-generation","title":"Unbiased General Annotated Dataset Generation","date":"2024-12-14","arxiv_id":"2412.10831","repositories_listed":0,"syntology":null},{"url":null,"slug":"variface-fair-and-diverse-synthetic-dataset","title":"VariFace: Fair and Diverse Synthetic Dataset Generation for Face Recognition","date":"2024-12-09","arxiv_id":"2412.06235","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-evolutionary-large-language-model-for","title":"An Evolutionary Large Language Model for Hallucination Mitigation","date":"2024-12-03","arxiv_id":"2412.02790","repositories_listed":0,"syntology":null},{"url":null,"slug":"know-your-rag-dataset-taxonomy-and-generation","title":"Know Your RAG: Dataset Taxonomy and Generation Strategies for Evaluating RAG Systems","date":"2024-11-29","arxiv_id":"2411.19710","repositories_listed":0,"syntology":null},{"url":null,"slug":"corrsynth-a-correlated-sampling-method-for","title":"CorrSynth -- A Correlated Sampling Method for Diverse Dataset Generation from LLMs","date":"2024-11-13","arxiv_id":"2411.08553","repositories_listed":0,"syntology":null},{"url":null,"slug":"hyperface-generating-synthetic-face","title":"HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere","date":"2024-11-13","arxiv_id":"2411.08470","repositories_listed":0,"syntology":null},{"url":null,"slug":"fineweb-edu-ar-machine-translated-corpus-to","title":"Fineweb-Edu-Ar: Machine-translated Corpus to Support Arabic Small Language Models","date":"2024-11-10","arxiv_id":"2411.06402","repositories_listed":0,"syntology":null},{"url":null,"slug":"fairness-utilization-trade-off-in-wireless","title":"Fairness-Utilization Trade-off in Wireless Networks with Explainable Kolmogorov-Arnold Networks","date":"2024-11-04","arxiv_id":"2411.01924","repositories_listed":0,"syntology":null},{"url":null,"slug":"simulating-user-agents-for-embodied","title":"Simulating User Agents for Embodied Conversational-AI","date":"2024-10-31","arxiv_id":"2410.23535","repositories_listed":0,"syntology":null},{"url":null,"slug":"synosis-image-synthesis-pipeline-for-machine","title":"SYNOSIS: Image synthesis pipeline for machine vision in metal surface inspection","date":"2024-10-18","arxiv_id":"2410.14844","repositories_listed":0,"syntology":null},{"url":null,"slug":"anchored-alignment-for-self-explanations","title":"Anchored Alignment for Self-Explanations Enhancement","date":"2024-10-17","arxiv_id":"2410.13216","repositories_listed":0,"syntology":null},{"url":null,"slug":"leveraging-fine-tuned-language-models-for","title":"FTSmartAudit: A Knowledge Distillation-Enhanced Framework for Automated Smart Contract Auditing Using Fine-Tuned LLMs","date":"2024-10-17","arxiv_id":"2410.13918","repositories_listed":0,"syntology":null},{"url":null,"slug":"pseudo-dataset-generation-for-out-of-domain","title":"Pseudo Dataset Generation for Out-of-Domain Multi-Camera View Recommendation","date":"2024-10-17","arxiv_id":"2410.13585","repositories_listed":0,"syntology":null},{"url":null,"slug":"autonomous-self-trained-channel-state","title":"Autonomous Self-Trained Channel State Prediction Method for mmWave Vehicular Communications","date":"2024-10-03","arxiv_id":"2410.02326","repositories_listed":0,"syntology":null},{"url":null,"slug":"healthq-unveiling-questioning-capabilities-of","title":"HealthQ: Unveiling Questioning Capabilities of LLM Chains in Healthcare Conversations","date":"2024-09-28","arxiv_id":"2409.19487","repositories_listed":0,"syntology":null}],"record_sha256":"b515b46095c2fc1991cce8980510c74cd44caa074f091b044e0a31daaa59aa8b","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}