{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:06:48Z","timestamp":1780765608603,"version":"3.54.1"},"reference-count":36,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001321","name":"National Research Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227777","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":7,"title":["A Multimodal LLM for Chart Understanding and Generation"],"prefix":"10.1109","author":[{"given":"Yucheng","family":"Han","sequence":"first","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fukun","family":"Yin","sequence":"additional","affiliation":[{"name":"Fudan University,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Yang","sequence":"additional","affiliation":[{"name":"Southeast University,Nanjing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhibin","family":"Wang","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gang","family":"Yu","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Fu","sequence":"additional","affiliation":[{"name":"Tencent,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University,Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","year":"2023","journal-title":"View in Article"},{"key":"ref2","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"ref3","article-title":"Glm-130b: An open bilingual pre-trained model","author":"Zeng","year":"2022"},{"key":"ref4","article-title":"Internlm: A multilingual language model with progressively enhanced capabilities","author":"Team","year":"2023"},{"key":"ref5","article-title":"Baichuan 2: Open large-scale language models","year":"2023"},{"key":"ref6","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref7","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"The dawn of lmms: Preliminary explorations with gpt-4v (ision)","author":"Yang","year":"2023"},{"key":"ref9","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref11","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref12","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref14","article-title":"Hallusionbench: You see what you think? or you think what you see? an image-context reasoning benchmark challenging for gpt-4v (ision), llava-1.5, and other multi-modality models","author":"Liu","year":"2023"},{"key":"ref15","first-page":"2263","article-title":"ChartQA: A benchmark for question answering about charts with visual and logical reasoning","volume-title":"Findings of the Association for Computational Linguistics: ACL 2022","author":"Masry"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.277"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref19","article-title":"Dall\u2022 e: Creating images from text","volume-title":"OpenAI blog","author":"Ramesh","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref21","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3571946"},{"key":"ref23","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref24","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref25","article-title":"Fine-tuning multimodal llms to follow zero-shot demonstrative instructions","author":"Li","year":"2023"},{"key":"ref26","article-title":"Llama-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref28","article-title":"Mmicl: Empowering vision-language model with multi-modal in-context learning","author":"Zhao","year":"2023"},{"key":"ref29","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref30","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.70"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref34","article-title":"Structchart: Perception, structuring, reasoning for visual chart understanding","author":"Xia","year":"2023"},{"key":"ref35","first-page":"18 893","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref36","article-title":"Chartgemma: Visual instruction-tuning for chart reasoning in the wild","author":"Masry","year":"2024c"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","location":"Rome, Italy","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227777.pdf?arnumber=11227777","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:11:10Z","timestamp":1763190670000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227777\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227777","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}