{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:40Z","timestamp":1777890100574,"version":"3.51.4"},"reference-count":85,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00047","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"426-436","source":"Crossref","is-referenced-by-count":0,"title":["ChartPoint: Guiding MLLMs with Grounding Reflection for Chart Reasoning"],"prefix":"10.1109","author":[{"given":"Zhengzhuo","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"SiNan","family":"Du","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yiyan","family":"Qi","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siwen","family":"Lu","sequence":"additional","affiliation":[{"name":"Beihang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengjin","family":"Xu","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Guo","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Anthropic","volume-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"key":"ref4","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Paligemma: A versatile 3b vlm for transfer","author":"Beyer","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Deepseek llm: Scaling open-source language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"proceedings of NeurIPS","author":"Brown","year":"2020"},{"key":"ref10","article-title":"Internlm2 technical report","author":"Cai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Chartbased reasoning: Transferring capabilities from 11 ms to vlms","volume-title":"proceedings of NAACL","author":"Carbune","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"ref13","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref17","article-title":"Internlmxcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Insight-v: Exploring long-chain visual reasoning with multimodal large language models","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Deepseek-r1: Incentivizing reasoning capability in 11 ms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Chartllama: A multimodal 11 m for chart understanding and generation","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32384"},{"key":"ref24","article-title":"Mistral 7b","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"1889318912","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"proceedings of ICML","author":"Lee","year":"2023"},{"key":"ref26","first-page":"2886","article-title":"Scaffolding coordinates to promote vision-language coordination in large multi-modal models","volume-title":"proceedings of COLING","author":"Lei","year":"2025"},{"key":"ref27","article-title":"Imagine while reasoning in space: Multimodal visualization-of-thought","author":"Li","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","first-page":"19730","article-title":"BLIP-2: bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"proceedings of ICML","author":"Li","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref30","article-title":"Sphinx: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Deepseek-v2: A strong, economical, and efficient mixture-of-experts language model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.714"},{"key":"ref35","article-title":"MMC: advancing multimodal chart understanding with large-scale instruction tuning","volume-title":"proceedings of ACL","author":"Liu","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref37","volume-title":"Llavanext: Improved reasoning, ocr, and world knowledge","author":"Liu","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.63317\/5mr38o4exfgq"},{"key":"ref40","article-title":"Decoupled weight decay regularization","volume-title":"proceedings of ICLR","author":"Loshchilov","year":"2019"},{"key":"ref41","article-title":"Deepseek-vl: Towards real-world vision-language understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref44","article-title":"Chartgemma: Visual instruction-tuning for chart reasoning in the wild","author":"Masry","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01367"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29844"},{"key":"ref49","article-title":"Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","volume-title":"Gpt-4o: A multimodal large language model","year":"2024"},{"key":"ref51","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref52","first-page":"8612","article-title":"Visual cot: Advancing multi-modal language models with a comprehensive dataset and benchmark for chain-of-thought reasoning","volume-title":"proceedings of NeurIPS","author":"Shao","year":"2025"},{"key":"ref53","article-title":"Intern: A new learning paradigm towards general vision","author":"Shao","year":"2021","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Efficient reasoning with hidden thinking","author":"Shen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Gemma: Open models based on gemini research and technology","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"DOMINO: A dual-system for multi-step visual language reasoning","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","first-page":"113569","article-title":"Charxiv: Charting gaps in realistic chart understanding in multimodal 11 ms","volume":"37","author":"Wang","year":"2025","journal-title":"proceeding of NeurIPS"},{"key":"ref61","first-page":"24824","article-title":"Chain-ofthought prompting elicits reasoning in large language models","volume-title":"proceedings of NeurIPS","author":"Wei","year":"2022"},{"key":"ref62","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3607618"},{"key":"ref64","article-title":"Llavacot: Let vision language models reason step-by-step","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Chartadapter: Large vision-language model for chart summarization","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Chartbench: A benchmark for complex visual reasoning in charts","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Chartmoe: Mixture of diversely aligned expert connector for chart understanding","volume-title":"proceedings of ICLR","author":"Xu","year":"2025"},{"key":"ref68","article-title":"xgenmm (blip-3): A family of open large multimodal models","author":"Xue","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-70533-5_26"},{"key":"ref70","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"Qwen2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Askchart: Universal chart understanding through textual enhancement","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref74","article-title":"mplug-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref75","article-title":"mplug-owl2: Revolutionizing multi-modal large language model with modality collaboration","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.112"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2026.104745"},{"key":"ref78","article-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref79","article-title":"Tinyllama: An open-source small language model","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref80","article-title":"Multimodal chain-of-thought reasoning in language models","author":"Zhang","year":"2024","journal-title":"TMLR"},{"key":"ref81","article-title":"Judging 11 m -as-a-judge with mt -bench and chatbot arena","volume-title":"proceedings of NeurIPS","author":"Zheng","year":"2023"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-demos.38"},{"key":"ref83","article-title":"Evaluation of openai o1: Opportunities and challenges of agi","author":"Zhong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1202"},{"key":"ref85","article-title":"Synthesize step-by-step: Tools, templates and 11 ms as data generators for reasoning-based chart vqa","volume-title":"proceedings of CVPR","author":"Zhuowan","year":"2024"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444854.pdf?arnumber=11444854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:33Z","timestamp":1777613433000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444854\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":85,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00047","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}