{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T20:02:59Z","timestamp":1776110579423,"version":"3.50.1"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172398"],"award-info":[{"award-number":["62172398"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Basic and Applied Basic Research Foundation","award":["2024A04J6462"],"award-info":[{"award-number":["2024A04J6462"]}]},{"name":"Guangzhou Basic and Applied Basic Research Foundation","award":["2023A03J0142"],"award-info":[{"award-number":["2023A03J0142"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tvcg.2024.3456159","type":"journal-article","created":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T19:06:21Z","timestamp":1725995181000},"page":"525-535","source":"Crossref","is-referenced-by-count":17,"title":["Advancing Multimodal Large Language Models in Chart Question Answering with Visualization-Referenced Instruction Tuning"],"prefix":"10.1109","volume":"31","author":[{"given":"Xingchen","family":"Zeng","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Haichuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Yilin","family":"Ye","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"given":"Wei","family":"Zeng","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Color histograms in image retrieval","year":"2024"},{"key":"ref2","article-title":"Semd-edup: Data-efficient learning at web-scale through semantic deduplication","author":"Abbas","year":"2023","journal-title":"arXiv"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.279"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3174168"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.185"},{"key":"ref8","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown","year":"2020"},{"key":"ref9","volume-title":"Readings in information visualization: using vision to think","author":"Card","year":"1999"},{"key":"ref10","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01311","article-title":"Honeybee: Locality-enhanced projector for muitimodal llm","volume-title":"Proc. CVPR","author":"Cha","year":"2024"},{"key":"ref11","volume-title":"Chartblocks. Online chart builder","year":"2017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3054916"},{"key":"ref13","article-title":"Shikra: Unleashing multimodal llm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2020.3030338"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3213565"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2022.3209468"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3155440"},{"key":"ref19","article-title":"Do LLMs work on charts? designing few-shot prompts for chart question answering and summarization","author":"Do","year":"2023","journal-title":"arXiv"},{"key":"ref20","article-title":"What makes for good visual instructions? synthesizing complex visual reasoning instructions for visual instruction tuning","author":"Du","year":"2023","journal-title":"arXiv"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581406"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3233389"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2865138"},{"key":"ref24","article-title":"Chartllama: A multimodal 11m for chart understanding and generation","author":"Han","year":"2023","journal-title":"arXiv"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"arXiv"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14573"},{"key":"ref28","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2022","journal-title":"Proc. ICLR"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300358"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376467"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref33","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642943"},{"key":"ref35","first-page":"18893","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","author":"Lee","year":"2023","journal-title":"Proc. ICML"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2598920"},{"key":"ref37","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume-title":"Proc. NeurIPS","volume":"33","author":"Lewis","year":"2020"},{"key":"ref38","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume-title":"Proc. NeurIPS","volume":"36","author":"Li","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3114863"},{"key":"ref40","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"Proc. ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.70"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref47","volume-title":"Llava-next: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref48","first-page":"34892","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Proc. NeurIPS"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2021.3114874"},{"key":"ref52","article-title":"Feast your eyes: Mixture-of-resolution adaptation for multimodal large language models","author":"Luo","year":"2024","journal-title":"arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457261"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref57","article-title":"Chartas-sisstant: A universal chart multimodal language model via chart-to-table pretraining and multitask instruction tuning","author":"Meng","year":"2024","journal-title":"arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/wacv45572.2020.9093523"},{"key":"ref59","volume-title":"OpenAI. gpt-4-vision-preview","year":"2024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14809"},{"key":"ref61","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford","year":"2021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.21428\/594757db.0b1f96f6"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref64","article-title":"Chartmimic: Evaluating lmm\u2019s cross-modal reasoning capability via chart-to-code generation","author":"Shi","year":"2024","journal-title":"arXiv"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.01.002"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"ref67","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv"},{"issue":"11","key":"ref68","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-industry.64"},{"key":"ref70","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Proc. NeurIPS"},{"key":"ref71","first-page":"16133","article-title":"Con-vNeXt V2: Co-designing and scaling convnets with masked autoencoders","volume-title":"Proc. CVPR","author":"Woo","year":"2023"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14832"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3326913"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2024.04.003"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3229023"},{"key":"ref76","article-title":"Gpt4roi: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv"},{"key":"ref77","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"Proc. NeurIPS"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/10766346\/10670526.pdf?arnumber=10670526","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:37:36Z","timestamp":1732667856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10670526\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":77,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2024.3456159","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}