{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T11:59:22Z","timestamp":1793966362150,"version":"4.8.0"},"reference-count":51,"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"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DP210102801,FT240100820"],"award-info":[{"award-number":["DP210102801,FT240100820"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["AST-2406729"],"award-info":[{"award-number":["AST-2406729"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00255","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2653-2663","source":"Crossref","is-referenced-by-count":7,"title":["Effective Training Data Synthesis for Improving MLLM Chart Understanding"],"prefix":"10.1109","author":[{"given":"Yuwei","family":"Yang","sequence":"first","affiliation":[{"name":"Australian National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zeyu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhong","family":"Hou","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuowan","family":"Li","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gaowen","family":"Liu","sequence":"additional","affiliation":[{"name":"Cisco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Payani","sequence":"additional","affiliation":[{"name":"Cisco"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan-Sen","family":"Ting","sequence":"additional","affiliation":[{"name":"Ohio State University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Australian National University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.383"},{"key":"ref2","author":"Abdin","year":"2024","journal-title":"Phi-3 technical report: A highly capable language model locally on your phone"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.288"},{"key":"ref4","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref5","first-page":"7","volume-title":"Introducing claude 3.5 sonnet","year":"2024"},{"key":"ref6","author":"Bai","year":"2025","journal-title":"Qwen2. 5-vl technical report"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-naacl.62"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"ref10","first-page":"2","author":"Cheng","year":"2024","journal-title":"On domain-specific post-training for multimodal large language models"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn64981.2025.11227777"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.172"},{"issue":"2","key":"ref13","first-page":"6","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680790"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32383"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00868"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref19","first-page":"2","author":"Kahou","year":"2017","journal-title":"Figureqa: An annotated figure dataset for visual reasoning"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.811"},{"key":"ref21","first-page":"18893","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"International Conference on Machine Learning (ICML)","author":"Lee"},{"key":"ref22","volume-title":"Llava-next: Stronger 11 ms supercharge multimodal capabilities in the wild (2024)","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01292"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-27806-0_1008"},{"key":"ref27","first-page":"3","author":"Liu","year":"2024","journal-title":"Synthvlm: High-efficiency and high-quality synthetic data for vision language models"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref34","first-page":"3","author":"Rodriguez","year":"2023","journal-title":"Starvector: Generating scalable vector graphics code from images"},{"key":"ref35","first-page":"5","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref36","first-page":"3","author":"Shi","year":"2024","journal-title":"Chartmimic: Evaluating 1 mm \u2019s cross-modal reasoning capability via chart-to-code generation"},{"key":"ref37","article-title":"Charxiv: Charting gaps in realistic chart understanding in multimodal 11 ms","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref38","author":"Xia","year":"2023","journal-title":"Structchart: Perception, structuring, reasoning for visual chart understanding"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3607618"},{"key":"ref40","first-page":"3","author":"Xing","year":"2024","journal-title":"Empowering 11 ms to understand and generate complex vector graphics"},{"key":"ref41","author":"Xu","year":"2023","journal-title":"Chartbench: A benchmark for complex visual reasoning in charts"},{"key":"ref42","first-page":"2","author":"Xu","year":"2024","journal-title":"Chartmoe: Mixture of expert connector for advanced chart understanding"},{"key":"ref43","first-page":"2","author":"Yang","year":"2024","journal-title":"Askchart: Universal chart understanding through textual enhancement"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.701"},{"key":"ref45","author":"Yao","year":"2024","journal-title":"Minicpm-v: A gpt-4v level mllm on your phone"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref47","first-page":"2","article-title":"Lamm: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","volume":"36","author":"Yin","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.640"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3456159"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1163\/9789004337862__com_161212"},{"key":"ref51","first-page":"2","author":"Zhang","year":"2024","journal-title":"Tinychart: Efficient chart understanding with visual token merging and program-of-thoughts learning"}],"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\/11444344.pdf?arnumber=11444344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:06:27Z","timestamp":1777611987000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00255","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}