{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:25:00Z","timestamp":1774419900845,"version":"3.50.1"},"reference-count":46,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887698","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["LaTeXNet: A Specialized Model for Converting Visual Tables and Equations to LaTeX Code"],"prefix":"10.1109","author":[{"given":"Renqiu","family":"Xia","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziming","family":"Feng","sequence":"additional","affiliation":[{"name":"China Merchants Bank Credit Card Center"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huanxi","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boan","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junchi","family":"Yan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26308"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2352\/issn.2168-3204.2023.20.1.10"},{"key":"ref3","article-title":"Opendatalab: Empowering general artificial intelligence with open datasets","volume":"abs\/2407.13773","author":"He","year":"2024","journal-title":"ArXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68790-8_50"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1242572.1242583"},{"key":"ref6","article-title":"Tapex: Table pre-training via learning a neural sql executor","author":"Liu","year":"2022","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/761"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2402536.2402585"},{"key":"ref9","article-title":"Ambiguity and constraint in mathematical expression recognition","author":"Miller","year":"1998","journal-title":"AAAI\/IAAI"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/958220.958239"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.06.017"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.609"},{"key":"ref13","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref14","article-title":"Internlm: A multilingual language model with progressively enhanced capabilities","year":"2023"},{"key":"ref15","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref17","article-title":"Dynamic multimodal evaluation with flexible complexity by vision-language bootstrapping","volume":"abs\/2410.08695","author":"Yang","year":"2024","journal-title":"ArXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.493"},{"key":"ref19","article-title":"Unimernet: A universal network for real-world mathematical expression recognition","volume":"abs\/2404.15254","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref20","article-title":"Cdm: A reliable metric for fair and accurate formula recognition evaluation","volume":"abs\/2409.03643","author":"Wang","year":"2024","journal-title":"ArXiv"},{"key":"ref21","article-title":"Structchart: On the schema, metric, and augmentation for visual chart understanding","volume":"abs\/2309.11268","author":"Xia","year":"2024","journal-title":"ArXiv"},{"key":"ref22","article-title":"Chartx & chartvlm: A versatile benchmark and foundation model for complicated chart reasoning","volume":"abs\/2402.12185","author":"Xia","year":"2024","journal-title":"ArXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-eacl.83"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.335"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref26","article-title":"Geox: Geometric problem solving through unified formalized vision-language pre-training","volume":"abs\/2412.11863","author":"Xia","year":"2024","journal-title":"ArXiv"},{"key":"ref27","article-title":"Gpt-4 technical report","volume":"abs\/2303.08774","year":"2023","journal-title":"ArXiv"},{"key":"ref28","article-title":"Mathpix api"},{"key":"ref29","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref31","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","author":"Lee","year":"2022","journal-title":"ICML"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref33","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"Levenshtein","year":"1965","journal-title":"Soviet physics. Doklady"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/234034a0"},{"key":"ref35","volume-title":"Data Mining: Concepts and Techniques","author":"Han","year":"2012"},{"key":"ref36","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"ACL"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00520"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2911996.2912035"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/694"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00315"},{"key":"ref41","article-title":"Graph neural networks are inherently good generalizers: Insights by bridging gnns and mlps","author":"Yang","year":"2023","journal-title":"ICLR"},{"key":"ref42","article-title":"Nodeformer: A scalable graph structure learning transformer for node classification","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref43","article-title":"Sgformer: Simplifying and empowering transformers for large-graph representations","author":"Wu","year":"2023","journal-title":"NeurIPS"},{"key":"ref44","article-title":"The policy-gradient placement and generative routing neural networks for chip design","author":"Cheng","year":"2022","journal-title":"NeurIPS"},{"key":"ref45","article-title":"ubrouter: Learning global routing via hub generation and pin-hub connection","author":"Du","year":"2023","journal-title":"NeurIPS"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00893"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887698.pdf?arnumber=10887698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:18Z","timestamp":1774416318000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887698","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}