{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:17:15Z","timestamp":1777889835736,"version":"3.51.4"},"reference-count":34,"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\/501100000038","name":"Hong Kong Research Grants Council Early Career Scheme","doi-asserted-by":"publisher","award":["22200824"],"award-info":[{"award-number":["22200824"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306090"],"award-info":[{"award-number":["62306090"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00027","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"208-217","source":"Crossref","is-referenced-by-count":0,"title":["Bootstrapping Grounded Chain-of-Thought in Multimodal Llms for Data-Efficient Model Adaptation"],"prefix":"10.1109","author":[{"given":"Jiaer","family":"Xia","sequence":"first","affiliation":[{"name":"Hong Kong Baptist University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingkui","family":"Tong","sequence":"additional","affiliation":[{"name":"Sichuan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Shao","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02506"},{"key":"ref2","article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Chartllama: A multimodal 11 m for chart understanding and generation","author":"Han","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1613"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref11","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1580"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref14","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref16","author":"Loshchilov","year":"2019","journal-title":"Decoupled weight decay regularization"},{"key":"ref17","article-title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref19","article-title":"Chartgemma: Visual instruction-tuning for chart reasoning in the wild","author":"Masry","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.463"},{"key":"ref21","article-title":"Selfcheck: Using 11 ms to zero-shot check their own step-by-step reasoning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Miao"},{"key":"ref22","article-title":"Im2text: Describing images using 1 million captioned photographs","volume":"24","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-long.109"},{"key":"ref25","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"In NeurIPS Workshop Datacentric AI. J\u00fclich Supercomputing Center","author":"Schuhmann","year":"2021"},{"key":"ref26","first-page":"arXiv-2403","article-title":"Visual cot: Unleashing chain-of-thought reasoning in multi-modal language models","author":"Shao","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1330"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref30","article-title":"Grounded chain-of-thought for multimodal large language models","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Visionary-r1: Mitigating shortcuts in visual reasoning with reinforcement learning","author":"Xia","year":"2025","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02184"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.254"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.540"}],"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\/11446267.pdf?arnumber=11446267","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:21:34Z","timestamp":1777612894000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446267\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00027","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}