{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T17:30:24Z","timestamp":1773423024116,"version":"3.50.1"},"reference-count":83,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T00:00:00Z","timestamp":1762992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>\n                    Multi-modal multi-task (M3T) foundation models (FMs) have recently shown transformative potential in artificial intelligence, with emerging applications in education. However, their deployment in real-world educational settings is hindered by privacy regulations, data silos, and limited domain-specific data availability. We introduce M3T Federated Foundation Models (FedFMs) for education: a paradigm that integrates federated learning (FL) with M3T FMs to enable collaborative, privacy-preserving training across decentralized institutions while accommodating diverse modalities and tasks. Subsequently, this perspective paper aims to unveil M3T FedFMs as a promising yet underexplored approach to the education community, explore its potentials, and reveal its related future research directions. We outline how M3T FedFMs can advance three critical pillars of next-generation intelligent education systems:\n                    <jats:italic>(i) privacy preservation<\/jats:italic>\n                    , by keeping sensitive multi-modal student and institutional data local;\n                    <jats:italic>(ii) personalization<\/jats:italic>\n                    , through modular architectures enabling tailored models for students, instructors, and institutions; and\n                    <jats:italic>(iii) equity and inclusivity<\/jats:italic>\n                    , by facilitating participation from underrepresented and resource-constrained entities. We finally identify various open research challenges, including studying of (i) inter-institution heterogeneous privacy regulations, (ii) the non-uniformity of data modalities' characteristics, (iii) the unlearning approaches for M3T FedFMs, (iv) the continual learning frameworks for M3T FedFMs, and (v) M3T FedFM model interpretability, which must be collectively addressed for practical deployment.\n                  <\/jats:p>","DOI":"10.3389\/frai.2025.1683960","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:31:17Z","timestamp":1763037077000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Bringing multi-modal multi-task federated foundation models to education domain: prospects and challenges"],"prefix":"10.3389","volume":"8","author":[{"given":"Kasra","family":"Borazjani","sequence":"first","affiliation":[]},{"given":"Naji","family":"Khosravan","sequence":"additional","affiliation":[]},{"given":"Rajeev","family":"Sahay","sequence":"additional","affiliation":[]},{"given":"Bita","family":"Akram","sequence":"additional","affiliation":[]},{"given":"Seyyedali","family":"Hosseinalipour","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,11,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.009.2300501","article-title":"Hierarchical federated foundation models over wireless networks for multi-modal multi-task intelligence: Integration of edge learning with D2D\/P2P-enabled fog learning architectures","author":"Abdisarabshali","year":"2025","journal-title":"arXiv"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"B3","first-page":"4424","article-title":"\u201cNo task left behind: Multi-task learning of knowledge tracing and option tracing for better student assessment\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"An","year":"2022"},{"key":"B4","doi-asserted-by":"publisher","first-page":"96","DOI":"10.21061\/jots.v40i2.a.4","article-title":"Augmented reality applications in education. J","volume":"40","author":"Antonioli","year":"2014","journal-title":"Technol. Stud"},{"key":"B5","doi-asserted-by":"publisher","first-page":"10181","DOI":"10.3390\/ijerph191610181","article-title":"Reducing anxiety and social stress in primary education: a breath-focused heart rate variability biofeedback intervention","volume":"19","author":"Aranberri-Ruiz","year":"2022","journal-title":"Int. J. Environm. Res. Public Health"},{"key":"B6","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1145\/3287324.3287430","article-title":"\u201cApplying machine learning to improve curriculum design\u201d","volume-title":"Proceedings of the 50th ACM Technical Symposium on Computer Science Education","author":"Ball","year":"2019"},{"key":"B7","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.3390\/ijerph19031192","article-title":"Artificial intelligence enabled personalised assistive tools to enhance education of children with neurodevelopmental disorders\u2014a review","volume":"19","author":"Barua","year":"2022","journal-title":"Int. J. Environm. Res. Public Health"},{"key":"B8","article-title":"Redefining non-iid data in federated learning for computer vision tasks: Migrating from labels to embeddings for task-specific data distributions","author":"Borazjani","year":"","journal-title":"arXiv"},{"key":"B9","article-title":"Multi-modal multi-task (M3T) federated foundation models for embodied AI: Potentials and challenges for edge integration","author":"Borazjani","year":"","journal-title":"arXiv"},{"key":"B10","doi-asserted-by":"publisher","first-page":"556","DOI":"10.1109\/TMI.2024.3450855","article-title":"Multi-modal federated learning for cancer staging over non-iid datasets with unbalanced modalities","volume":"44","author":"Borazjani","year":"2024","journal-title":"IEEE Trans. Med. Imag"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/09523987.2014.889400","article-title":"Augmented reality in education-cases, places and potentials","volume":"51","author":"Bower","year":"2014","journal-title":"Educ. Media Int"},{"key":"B12","first-page":"1877","article-title":"\u201cLanguage models are few-shot learners,\u201d","volume-title":"Advances in Neural Information Processing Systems 33","author":"Brown","year":"2020"},{"key":"B13","first-page":"19","article-title":"\u201cTowards taming the resource and data heterogeneity in federated learning\u201d","volume-title":"2019 USENIX Conference on Operational Machine Learning (OpML 19)","author":"Chai","year":"2019"},{"key":"B14","doi-asserted-by":"publisher","first-page":"1855","DOI":"10.1109\/TIFS.2023.3255171","article-title":"Privacy-preserving federated learning via functional encryption, revisited","volume":"18","author":"Chang","year":"2023","journal-title":"IEEE Trans. Inform. Forens. Security"},{"key":"B15","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TBDATA.2022.3159236","article-title":"Practical attribute reconstruction attack against federated learning","volume":"10","author":"Chen","year":"2022","journal-title":"IEEE Trans. Big Data"},{"key":"B16","doi-asserted-by":"publisher","first-page":"11285","DOI":"10.1609\/aaai.v38i10.29007","article-title":"FedDAT: an approach for foundation model finetuning in multi-modal heterogeneous federated learning","volume":"38","author":"Chen","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1101\/2022.08.06.503062","article-title":"Interpretable rna foundation model from unannotated data for highly accurate rna structure and function predictions","author":"Chen","year":"2022","journal-title":"arXiv"},{"key":"B18","doi-asserted-by":"publisher","first-page":"11311","DOI":"10.1609\/aaai.v38i10.29010","article-title":"On disentanglement of asymmetrical knowledge transfer for modality-task agnostic federated learning","volume":"38","author":"Chen","year":"2024","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B19","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"J. Mach. Learn. Res"},{"key":"B20","first-page":"3033","article-title":"\u201cMitigating biases in student performance prediction via attention-based personalized federated learning\u201d","author":"Chu","year":"2022","journal-title":"Proceedings of the 31st ACM International Conference on Information"},{"key":"B21","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/TETC.2024.3407716","article-title":"Multi-layer personalized federated learning for mitigating biases in student predictive analytics","volume":"10","author":"Chu","year":"2024","journal-title":"IEEE Trans. Emerg. Topics Comput"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"arXiv"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.11714","article-title":"The transition from centralized machine learning to federated learning for mental health in education: A survey of current methods and future directions","author":"Ebrahimi","year":"2025","journal-title":"arXiv"},{"key":"B24","doi-asserted-by":"publisher","first-page":"22359","DOI":"10.1109\/ACCESS.2022.3151670","article-title":"Differential privacy for deep and federated learning: A survey","volume":"10","author":"El Ouadrhiri","year":"2022","journal-title":"IEEE Access"},{"key":"B25","doi-asserted-by":"publisher","first-page":"43","DOI":"10.3390\/data8020043","article-title":"Federated learning for data analytics in education","volume":"8","author":"Fachola","year":"2023","journal-title":"Data"},{"key":"B26","doi-asserted-by":"publisher","first-page":"94","DOI":"10.3390\/fi13040094","article-title":"Privacy preserving machine learning with homomorphic encryption and federated learning","volume":"13","author":"Fang","year":"2021","journal-title":"Future Internet"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.19389","article-title":"Federated sketching lora: On-device collaborative fine-tuning of large language models","author":"Fang","year":"2025","journal-title":"arXiv"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.","article-title":"On championing foundation models: From explainability to interpretability","author":"Fu","year":"2024","journal-title":"arXiv"},{"key":"B29","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1609\/aaai.v34i01.5406","article-title":"Predictive student modeling in educational games with multi-task learning","volume":"34","author":"Geden","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21783","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv"},{"key":"B31","doi-asserted-by":"publisher","first-page":"124","DOI":"10.20853\/37-5-5815","article-title":"Can virtual reality have a positive influence on student engagement?","volume":"37","author":"Grewe","year":"2023","journal-title":"South Afri. J. Higher Educ"},{"key":"B32","doi-asserted-by":"publisher","first-page":"13","DOI":"10.14201\/ADCAIJ2014381326","article-title":"Developing multimodal conversational agents for an enhanced e-learning experience","volume":"3","author":"Griol","year":"2014","journal-title":"ADCAIJ"},{"key":"B33","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1145\/3404709.3404751","article-title":"Pedagogical data analysis via federated learning toward education 4.0","volume":"4","author":"Guo","year":"2020","journal-title":"Am. J. Educ. Inform. Technol"},{"key":"B34","first-page":"3056","article-title":"\u201cScattering prompt tuning: A fine-tuned foundation model for sar object recognition\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Guo","year":"2024"},{"key":"B35","doi-asserted-by":"publisher","author":"Halimi","year":"2022","DOI":"10.48550\/arXiv."},{"key":"B36","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1007\/s10579-020-09517-1","article-title":"AI2D-RST: a multimodal corpus of 1000 primary school science diagrams","volume":"55","author":"Hiippala","year":"2021","journal-title":"Language Resources and Eval"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.","article-title":"Facilitating instructors-LLM collaboration for problem design in introductory programming classrooms","author":"Hoq","year":"2025","journal-title":"arXiv"},{"key":"B38","article-title":"\u201cPrivacy-preserving distributed link predictions among peers in online classrooms using federated learning\u201d","volume-title":"Conference on Educational Data Mining (EDM)","author":"Hridi","year":"2025"},{"key":"B39","doi-asserted-by":"crossref","first-page":"297","DOI":"10.1609\/aaaiss.v3i1.31217","article-title":"\u201cRevolutionizing AI-assisted education with federated learning: A pathway to distributed, privacy-preserving, and debiased learning ecosystems\u201d","author":"Hridi","year":"2024","journal-title":"Proceedings of the AAAI Symposium Series"},{"key":"B40","doi-asserted-by":"publisher","first-page":"1115","DOI":"10.1038\/s41597-025-05426-6","article-title":"A multi-modal dataset for teacher behavior analysis in offline classrooms","volume":"12","author":"Huang","year":"2025","journal-title":"Scientific Data"},{"key":"B41","doi-asserted-by":"publisher","first-page":"100086","DOI":"10.1016\/j.caeai.2022.100086","article-title":"The use of a personalized learning approach to implementing self-regulated online learning","volume":"3","author":"Ingkavara","year":"2022","journal-title":"Comp. Educ.: Artif. Intellig"},{"key":"B42","first-page":"709","article-title":"\u201cVisual prompt tuning\u201d","volume-title":"European Conference on Computer Vision","author":"Jia","year":"2022"},{"key":"B43","first-page":"491","article-title":"\u201cOn assessing the faithfulness of LLM-generated feedback on student assignments\u201d","volume-title":"Proceedings of the 17th International Conference on Educational Data Mining","author":"Jia","year":"2024"},{"key":"B44","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1007\/s10648-024-09878-x","article-title":"The validity of heart rate variability (HRV) in educational research and a synthesis of recommendations","volume":"36","author":"Kim","year":"2024","journal-title":"Educ. Psychol. Rev"},{"key":"B45","doi-asserted-by":"publisher","first-page":"18","DOI":"10.3390\/digital3010002","article-title":"Location-based augmented reality for cultural heritage education: Creating educational, gamified location-based AR applications for the prehistoric lake settlement of dispilio","volume":"3","author":"Kleftodimos","year":"2023","journal-title":"Digital"},{"key":"B46","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1038\/s41539-025-00301-w","article-title":"On opportunities and challenges of large multimodal foundation models in education","volume":"10","author":"K\u00fcchemann","year":"2025","journal-title":"NPJ Sci. Learn"},{"key":"B47","first-page":"10194","article-title":"\u201cResSFL: A resistance transfer framework for defending model inversion attack in split federated learning\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Li","year":"2022"},{"key":"B48","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s13040-024-00414-9","article-title":"Open challenges and opportunities in federated foundation models towards biomedical healthcare","volume":"18","author":"Li","year":"2025","journal-title":"BioData Mining"},{"key":"B49","doi-asserted-by":"crossref","first-page":"1360574","DOI":"10.3389\/fpsyg.2024.1360574","article-title":"The impact of virtual reality on student engagement in the classroom-a critical review of the literature","volume":"15","author":"Lin","year":"2024","journal-title":"Front. Psychol"},{"key":"B50","doi-asserted-by":"publisher","first-page":"2745","DOI":"10.1109\/LSP.2024.3453200","article-title":"Mutual gradient inversion: Unveiling privacy risks of federated learning on multi-modal signals","volume":"31","author":"Liu","year":"2024","journal-title":"IEEE Signal Proc. Letters"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3679014","article-title":"A survey on federated unlearning: Challenges, methods, and future directions","volume":"57","author":"Liu","year":"2024","journal-title":"ACM Comp. Surv"},{"key":"B52","first-page":"39409","article-title":"\u201cDual-personalizing adapter for federated foundation models\u201d","author":"Long","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2310.02255","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv"},{"key":"B54","first-page":"1697","article-title":"\u201cInfographicvqa\u201d","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Mathew","year":"2022"},{"key":"B55","first-page":"1273","article-title":"\u201cCommunication-efficient learning of deep networks from decentralized data\u201d","volume-title":"Artificial Intelligence and","author":"McMahan","year":"2017"},{"key":"B56","first-page":"23215","article-title":"\u201cRetLLM-E: retrieval-prompt strategy for question-answering on student discussion forums\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Mitra","year":"2024"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2411.02725","article-title":"Leveraging LLM tutoring systems for non-native english speakers in introductory cs courses","author":"Molina","year":"2024","journal-title":"arXiv"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2409.20167","article-title":"Using large multimodal models to extract knowledge components for knowledge tracing from multimedia question information","author":"Moon","year":"2024","journal-title":"arXiv"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.05683","article-title":"Multi-modal multi-task federated foundation models for next-generation extended reality systems: Towards privacy-preserving distributed intelligence in AR\/VR\/MR","author":"Nadimi","year":"2025","journal-title":"arXiv"},{"key":"B60","first-page":"33","article-title":"Using machine learning algorithms to predict students' performance and improve learning outcome: A literature based review","volume":"4","author":"Ofori","year":"2020","journal-title":"J. Inform. Technol"},{"key":"B61","first-page":"60","article-title":"\u201cContinual learning with foundation models: An empirical study of latent replay\u201d","volume-title":"Conference on Lifelong Learning Agents","author":"Ostapenko","year":"2022"},{"key":"B62","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/3565287.3610278","article-title":"\u201cConnectivity-aware semi-decentralized federated learning over time-varying D2D networks\u201d","volume-title":"Proceedings of the Twenty-fourth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing","author":"Parasnis","year":"2023"},{"key":"B63","doi-asserted-by":"crossref","first-page":"118","DOI":"10.4324\/9780203731864-6","article-title":"\u201cStudent consent in learning analytics: the devil in the details?\u201d","volume-title":"Learning Analytics in Higher","author":"Prinsloo","year":"2018"},{"key":"B64","first-page":"8748","article-title":"\u201cLearning transferable visual models from natural language supervision\u201d","volume-title":"International Conference on Machine","author":"Radford","year":"2021"},{"key":"B65","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.09236","article-title":"Learning interpretable concepts: Unifying causal representation learning and foundation models","author":"Rajendran","year":"2024","journal-title":"arXiv"},{"key":"B66","author":"Rao","year":"2025","journal-title":"Leveraging Large Language Models to Promote AI-Infused Stem Problem-Solving for Middle School Students"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2304.08901","article-title":"Multimodal group activity dataset for classroom engagement level prediction","author":"Sabuncuoglu","year":"2023","journal-title":"arXiv"},{"key":"B68","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.11805","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv"},{"key":"B69","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2302.13971","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"key":"B70","doi-asserted-by":"publisher","first-page":"1418006","DOI":"10.3389\/feduc.2024.1418006","article-title":"Advanced large language models and visualization tools for data analytics learning","volume":"9","author":"Valverde-Rebaza","year":"2024","journal-title":"Front. Educ"},{"key":"B71","first-page":"95095","article-title":"\u201cMeasuring multimodal mathematical reasoning with math-vision dataset\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Wang","year":"2024"},{"key":"B72","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.05677","article-title":"Batched low-rank adaptation of foundation models","author":"Wen","year":"2023","journal-title":"arXiv"},{"key":"B73","doi-asserted-by":"publisher","first-page":"186","DOI":"10.18608\/jla.2025.8595","article-title":"Utilizing multimodal large language models for video analysis of posture in studying collaborative learning: a case study","volume":"12","author":"Whitehead","year":"2025","journal-title":"J. Learn. Analyt"},{"key":"B74","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3659205","article-title":"Topology-aware federated learning in edge computing: a comprehensive survey","volume":"56","author":"Wu","year":"2024","journal-title":"ACM Comp. Surv"},{"key":"B75","doi-asserted-by":"publisher","first-page":"3937","DOI":"10.3390\/app15073937","article-title":"A review of multimodal interaction in remote education: technologies, applications, and challenges","volume":"15","author":"Xie","year":"2025","journal-title":"Appl. Sci"},{"key":"B76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2505.16160","article-title":"Edubench: A comprehensive benchmarking dataset for evaluating large language models in diverse educational scenarios","author":"Xu","year":"2025","journal-title":"arXiv"},{"key":"B77","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1016\/j.chb.2017.12.037","article-title":"Review on portable eeg technology in educational research","volume":"81","author":"Xu","year":"2018","journal-title":"Computers in Human Behavior"},{"key":"B78","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/MIS.2024.3398191","article-title":"Foundation models for education: promises and prospects","volume":"39","author":"Xu","year":"2024","journal-title":"IEEE Intellig, Syst"},{"key":"B79","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.00365","article-title":"Low-rank adaptation for foundation models: a comprehensive review","author":"Yang","year":"2024","journal-title":"arXiv"},{"key":"B80","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3705725","article-title":"Recent advances of foundation language models-based continual learning: a survey","volume":"57","author":"Yang","year":"2025","journal-title":"ACM Comp. Surv"},{"key":"B81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.06580","article-title":"Towards general purpose medical ai: Continual learning medical foundation model","author":"Yi","year":"2023","journal-title":"arXiv"},{"key":"B82","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1177\/1477878518815340","article-title":"Learner privacy in moocs and virtual education","volume":"16","author":"Zeide","year":"2018","journal-title":"Theory Res. Educ"},{"key":"B83","first-page":"21682","article-title":"\u201cContrastive adapters for foundation model group robustness\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang","year":"2022"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1683960\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T12:31:25Z","timestamp":1763037085000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1683960\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,13]]},"references-count":83,"alternative-id":["10.3389\/frai.2025.1683960"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1683960","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,13]]},"article-number":"1683960"}}