{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:10:09Z","timestamp":1777889409317,"version":"3.51.4"},"reference-count":90,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00101","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1004-1015","source":"Crossref","is-referenced-by-count":0,"title":["Reinforcement Learning-Guided Data Selection Via Redundancy Assessment"],"prefix":"10.1109","author":[{"given":"Suorong","family":"Yang","sequence":"first","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peijia","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Furao","family":"Shen","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2192"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2384"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093562"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00521"},{"key":"ref5","article-title":"Why adversarial training of relu networks is difficult?","author":"Cheng","year":"2022","journal-title":"arXiv preprint arXiv"},{"issue":"240","key":"ref6","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","article-title":"A downsampled variant of imagenet as an alternative to the cifar datasets","author":"Chrabaszcz","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref8","article-title":"Selection via proxy: Efficient data selection for deep learning","author":"Coleman","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00365"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1080\/01969727308546046"},{"key":"ref13","first-page":"2881","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","volume":"33","author":"Feldman","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","volume-title":"Vissl","author":"Goyal","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"ref16","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref17","article-title":"Towards lossless dataset distillation via difficulty-aligned trajectory matching","author":"Guo","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","article-title":"Data-efficient training of cnns and transformers with coresets: A stability perspective","author":"Gupta","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1710"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref23","article-title":"Diversified batch selection for training acceleration","author":"Hong","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref24","article-title":"Donod: Robust and generalizable instruction fine-tuning for llms via model-intrinsic dataset pruning","author":"Hu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1477"},{"key":"ref27","first-page":"5464","article-title":"Grad-match: Gradient matching based data subset selection for efficient deep model training","volume-title":"In International Conference on Machine Learning","author":"Killamsetty"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i9.16988"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref30","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"In Proceedings of the 34th International Conference on Machine Learning - Volume 70","author":"Koh"},{"key":"ref31","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"In International conference on machine learning","author":"Koh"},{"key":"ref32","article-title":"Prism: A unified framework of parameterized submodular information measures for targeted data subset selection and summarization","volume-title":"In ThirtySixth AAAI Conference on Artificial Intelligence, AAAI","author":"Kothawade"},{"key":"ref33","author":"Krizhevsky","year":"2009","journal-title":"Learning multiple layers of features from tiny images"},{"key":"ref34","article-title":"Dr3: Valuebased deep reinforcement learning requires explicit regularization","author":"Kumar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Supervised pretraining can learn in-context reinforcement learning","volume":"36","author":"Lee","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3322540"},{"key":"ref37","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Design from policies: Conservative test-time adaptation for offline policy optimization","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref40","article-title":"Structured state space models for in-context reinforcement learning","volume":"36","author":"Lu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","article-title":"D2 pruning: Message passing for balancing diversity and difficulty in data pruning","author":"Maharana","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Language models are few-shot learners","author":"Mann","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Trivial or impossible - dichotomous data difficulty masks model differences (on imagenet and beyond)","volume-title":"International Conference on Learning Representations","author":"Meding"},{"key":"ref44","first-page":"6950","article-title":"Coresets for data-efficient training of machine learning models","volume-title":"In International Conference on Machine Learning","author":"Mirzasoleiman"},{"key":"ref45","article-title":"Asynchronous methods for deep reinforcement learning","author":"Mnih","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref46","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"In International conference on machine learning","author":"Mnih"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0851"},{"key":"ref48","article-title":"Bridging the gap between value and policy based reinforcement learning","volume":"30","author":"Nachum","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref49","article-title":"Data valuation without training of a model","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Nohyun"},{"key":"ref50","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume":"34","author":"Paul","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","first-page":"17848","article-title":"Adaptive second order coresets for data-efficient machine learning","volume-title":"In International Conference on Machine Learning","author":"Pooladzandi"},{"key":"ref52","article-title":"Infobatch: Lossless training speed up by unbiased dynamic data pruning","author":"Qin","year":"2023","journal-title":"arXiv preprint arXiv"},{"issue":"8","key":"ref53","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref55","article-title":"Accelerating deep learning with dynamic data pruning","author":"Raju","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2023.3315272"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref58","article-title":"Active learning for convolutional neural networks: A core-set approach","volume-title":"International Conference on Learning Representations","author":"Sener"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.120495"},{"key":"ref60","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1419"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10243"},{"key":"ref63","article-title":"Imagenet-hard: The hardest images remaining from a study of the power of zoom and spatial biases in image classification","volume":"36","author":"Taesiri","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref64","article-title":"Data pruning via moving-one-sample-out","volume":"36","author":"Tan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2348"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.88"},{"key":"ref67","article-title":"An empirical study of example forgetting during deep neural network learning","author":"Toneva","year":"2018","journal-title":"arXiv preprint arXiv"},{"issue":"11","key":"ref68","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Machine Learning Research"},{"key":"ref69","first-page":"1954","article-title":"Submodularity in data subset selection and active learning","volume-title":"In International conference on machine learning","author":"Wei"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553517"},{"key":"ref71","article-title":"Scalable trust-region method for deep reinforcement learning using kronecker-factored approximation","volume":"30","author":"Wu","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref72","article-title":"Moderate coreset: A universal method of data selection for real-world data-efficient deep learning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Xia","year":"2023"},{"key":"ref73","article-title":"Dataset pruning: Reducing training data by examining generalization influence","volume-title":"International Conference on Learning Representations","author":"Yang"},{"key":"ref74","article-title":"Not all data matters: An end-to-end adaptive dataset pruning framework for enhancing model performance and efficiency","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110204"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3592538"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_12"},{"key":"ref78","article-title":"A clip-powered framework for robust and generalizable data selection","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref79","article-title":"When dynamic data selection meets data augmentation","author":"Yang","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref80","article-title":"Nearly optimal vc-dimension and pseudo-dimension bounds for deep neural network derivatives","author":"Yang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref81","article-title":"B-coder: Value-based deep reinforcement learning for program synthesis","volume-title":"arXiv preprint arXiv","author":"Yu","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5467"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01150"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02477"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1605"},{"key":"ref86","article-title":"Dynamic tuning towards parameter and inference efficiency for vit adaptation","author":"Zhao","year":"2024","journal-title":"NeurIPS"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01845"},{"key":"ref88","article-title":"Coverage-centric coreset selection for high pruning rates","volume-title":"The Eleventh International Conference on Learning Representations","author":"Zheng"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01578"},{"key":"ref90","article-title":"Dataset distillation using neural feature regression","author":"Zhou","year":"2022","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444151.pdf?arnumber=11444151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:35Z","timestamp":1777612355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00101","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}