{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:54:50Z","timestamp":1772934890569,"version":"3.50.1"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"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":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402157","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5472-5481","source":"Crossref","is-referenced-by-count":0,"title":["Tackling Low-Resource K-12 Hand-Drawn Mathematics VQA: Unified Regularization with Compute-Aware Expert Token Architecture"],"prefix":"10.1109","author":[{"given":"Hai","family":"Li","sequence":"first","affiliation":[{"name":"Informatics for Education, University of Florida,Gainesville,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanli","family":"Xing","sequence":"additional","affiliation":[{"name":"Informatics for Education, University of Florida,Gainesville,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenglu","family":"Li","sequence":"additional","affiliation":[{"name":"Educational Psychology, University of Utah,Salt Lake City,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bailing","family":"Lyu","sequence":"additional","affiliation":[{"name":"Educational Psychology, Auburn University,Auburn,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-98465-5_32"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3636555.3636860"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-99264-3_39"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2024.3521744"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.clinicalnlp-1.21"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref8","article-title":"On the domain adaptation and generalization of pretrained language models: A survey","author":"Guo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"On domain-specific post-training for multimodal large language models","author":"Cheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s40593-024-00416-y"},{"key":"ref11","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1111\/bjet.13554"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.126508"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.352"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3657604.3662029"},{"key":"ref17","article-title":"Deplot: One-shot visual language reasoning by plot-to-table translation","author":"Liu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","first-page":"18893","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"International Conference on Machine Learning","author":"Lee","year":"2023"},{"key":"ref19","article-title":"On pre-training of multimodal language models customized for chart understanding","author":"Fan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"An introduction to visionlanguage modeling","author":"Bordes","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14573"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3483224"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.109163"},{"key":"ref24","article-title":"Plug-andplay vqa: Zero-shot vqa by conjoining large pretrained models with zero training","author":"Tiong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Visual large language models for generalized and specialized applications","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Simplot: Enhancing chart question answering by distilling essentials","author":"Kim","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"The quest for visual understanding: A journey through the evolution of visual question answering","author":"Pandey","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s13369-024-09067-6"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2025.03.005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s10956-025-10262-9"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18608\/jla.2025.8557"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3237025"},{"key":"ref33","article-title":"Vllavo: Mitigating visual gap through llms","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"crossref","first-page":"212","DOI":"10.1145\/3709026.3709059","article-title":"On enhancing adversarial robustness of large pretrained vision-language models","volume-title":"Proceedings of the 2024 8th International Conference on Computer Science and Artificial Intelligence","author":"Luo","year":"2024"},{"key":"ref36","article-title":"Exponential moving average of weights in deep learning: Dynamics and benefits","author":"Morales-Brotons","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456159"},{"key":"ref38","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","first-page":"19730","article-title":"Blip-2: Bootstrapping languageimage pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref40","article-title":"Gemma 3 technical report","author":"Team","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109229"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref45","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"Journal of machine learning research"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402157.pdf?arnumber=11402157","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T07:19:36Z","timestamp":1772867976000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402157\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402157","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}