{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T19:50:13Z","timestamp":1789069813540,"version":"build-2803163510"},"reference-count":21,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"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":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10687434","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":1,"title":["Maths: Multimodal Transformer-Based Human-Readable Solver"],"prefix":"10.1109","author":[{"given":"Yicheng","family":"Pan","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenrong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiefeng","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Du","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,NERC-SLIP"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianshu","family":"Zhang","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dan","family":"Liu","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Si","family":"Wei","sequence":"additional","affiliation":[{"name":"iFLYTEK Research,Hefei,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i02.5489"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.528"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.218"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/376"},{"key":"ref5","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023"},{"key":"ref6","article-title":"Siren\u2019s song in the ai ocean: A survey on hallucination in large language models","author":"Zhang","year":"2023"},{"key":"ref7","article-title":"Math-vista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/0600000018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/228"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.1"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3617680"},{"key":"ref15","article-title":"CTRL - A Conditional Transformer Language Model for Controllable Generation","author":"Keskar","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acldemos.30"},{"key":"ref17","article-title":"Plug and play language models: A simple approach to controlled text generation","volume-title":"ICLR","author":"Dathathri"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.334"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.46"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10687434.pdf?arnumber=10687434","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:30:13Z","timestamp":1727764213000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10687434\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10687434","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}