{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:41:44Z","timestamp":1791913304217,"version":"4.3.4"},"reference-count":35,"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"}],"funder":[{"DOI":"10.13039\/501100007937","name":"Peking University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007937","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889286","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Diagram Formalization Enhanced Multi-Modal Geometry Problem Solver"],"prefix":"10.1109","author":[{"given":"Zeren","family":"Zhang","sequence":"first","affiliation":[{"name":"Peking University,School of Mathematical Sciences,Beijing,China,100871"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo-Ku","family":"Cheng","sequence":"additional","affiliation":[{"name":"Peking University,School of Mathematical Sciences,Beijing,China,100871"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyang","family":"Deng","sequence":"additional","affiliation":[{"name":"Peking University,School of Mathematical Sciences,Beijing,China,100871"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lu","family":"Tian","sequence":"additional","affiliation":[{"name":"01.AI,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwen","family":"Ma","sequence":"additional","affiliation":[{"name":"Peking University,School of Mathematical Sciences,Beijing,China,100871"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziran","family":"Qin","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University,School of Electronic, Information and Electrical Engineering,China,200240"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaokai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China,200444"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Na","family":"Zhu","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China,200444"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tuo","family":"Leng","sequence":"additional","affiliation":[{"name":"Shanghai University,School of Computer Engineering and Science,China,200444"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Shao","year":"2024","journal-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models"},{"key":"ref2","article-title":"Qwen-2 math: Enhancing math reasoning for language models"},{"key":"ref3","author":"Luo","year":"2023","journal-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct"},{"key":"ref4","author":"Lu","year":"2023","journal-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts"},{"key":"ref5","author":"Wang","year":"2024","journal-title":"Measuring multimodal mathematical reasoning with math-vision dataset"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.73"},{"key":"ref7","author":"Gao","year":"2023","journal-title":"G-llava: Solving geometric problem with multi-modal large language model"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref9","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref10","author":"Young","year":"2024","journal-title":"Yi: Open foundation models by 01. ai"},{"key":"ref11","author":"Lu","year":"2024","journal-title":"Deepseek-vl: towards real-world vision-language understanding"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-79876-5_33"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.44"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06747-5"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3390\/sym16040421"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-1029"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/376"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref21","author":"Zhang","year":"2023","journal-title":"Formalgeo: The first step toward human-like imo-level geometric automated reasoning"},{"key":"ref22","article-title":"Geogebra: Dynamic mathematics for everyone","year":"2024"},{"key":"ref23","article-title":"Matlab","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref25","author":"Yang","year":"2024","journal-title":"Qwen2 technical report"},{"key":"ref26","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref27","author":"Xin","year":"2024","journal-title":"Deepseek-prover-v1.5: Harnessing proof assistant feedback for reinforcement learning and monte-carlo tree search"},{"key":"ref28","author":"Bai","year":"2023","journal-title":"Qwen-vl: A frontier large vision-language model with versatile abilities"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-79876-5_37"},{"key":"ref30","author":"Dubey","year":"2024","journal-title":"The llama 3 herd of models"},{"key":"ref31","article-title":"Qwen2-vl: To see the world more clearly","author":"Team","year":"2024"},{"key":"ref32","author":"Abdin","year":"2024","journal-title":"Phi-3 technical report: A highly capable language model locally on your phone"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref34","article-title":"Llava-next: Stronger llms supercharge multimodal capabilities in the wild","author":"Li","year":"2024"},{"key":"ref35","author":"Achiam","year":"2023","journal-title":"Gpt-4 technical report"}],"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\/10889286.pdf?arnumber=10889286","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:09Z","timestamp":1774416309000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889286\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889286","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}