{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:17Z","timestamp":1777865297579,"version":"3.51.4"},"reference-count":64,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306261"],"award-info":[{"award-number":["62306261"]}],"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\/iccv51701.2025.00289","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3011-3022","source":"Crossref","is-referenced-by-count":0,"title":["Chimera: Improving Generalist Model with Domain-Specific Experts"],"prefix":"10.1109","author":[{"given":"Tianshuo","family":"Peng","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong,MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingsheng","family":"Li","sequence":"additional","affiliation":[{"name":"College of Future Information Technology, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiakang","family":"Yuan","sequence":"additional","affiliation":[{"name":"College of Future Information Technology, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongbin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renqiu","family":"Xia","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renrui","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Mao","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aojun","family":"Zhou","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Botian","family":"Shi","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Future Information Technology, Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Yue","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,MMLab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"The claude 3 model family: Opus, sonnet, haiku"},{"key":"ref2","article-title":"Pixtral 12b","author":"Agrawal","year":"2024","journal-title":"arXiv preprint"},{"key":"ref3","volume-title":"The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"issue":"2","key":"ref4","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","volume":"1","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw63382.2024.00188"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02496"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","article-title":"Benchmarking and improving detail image caption","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"G-llava: Solving geometric problem with multi-modal large language model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Mme-cot: Benchmarking chain-of-thought in large multimodal models for reasoning quality, robustness, and efficiency","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","author":"Li","year":"2024","journal-title":"Llava-next: Stronger llms supercharge multimodal capabilities in the wild"},{"key":"ref16","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref18","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref19","article-title":"M3dbench: Let\u2019s instruct large models with multi-modal 3d prompts","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Omnicorpus: An unified multimodal corpus of 10 billion-level images interleaved with text","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref23","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":"ref24","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.660"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017"},{"key":"ref28","article-title":"Mathvista: Evaluating mathematical reasoning of foundation models in visual contexts","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","author":"Lu","year":"2024","journal-title":"Ovis: Structural embedding alignment for multimodal large language model"},{"key":"ref30","article-title":"Omnicaptioner: One captioner to rule them all","author":"Lu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.906"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.619"},{"key":"ref34","article-title":"Chartgemma: Visual instruction-tuning for chart reasoning in the wild","author":"Masry","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref36","volume-title":"Gpt-4v","year":"2023"},{"key":"ref37","volume-title":"Hello gpt-4o","year":"2024"},{"key":"ref38","article-title":"Im2text: Describing images using 1 million captioned photographs","author":"Ordonez","year":"2011","journal-title":"Advances in neural information processing systems"},{"key":"ref39","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Reid","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref42","article-title":"Mome: Mixture of multimodal experts for generalist multimodal large language models","author":"Shen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.268"},{"key":"ref44","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Novelseek: When agent becomes the scientist-building closed-loop system from hypothesis to verification","author":"Team","year":"2025","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Mineru: An open-source solution for precise document content extraction","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","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":"ref51","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":"ref52","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"General ocr theory: Towards ocr-2.0 via a unified end-to-end model","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Structchart: Perception, structuring, reasoning for visual chart understanding","author":"Xia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Geox: Geometric problem solving through unified formalized vision-language pretraining","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Docgenome: An open largescale scientific document benchmark for training and testing multi-modal large language models","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2025.3607618"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref59","article-title":"Mme-reasoning: A comprehensive benchmark for logical reasoning in mllms","author":"Yuan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Mavis: Mathematical visual instruction tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_10"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.493"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i24.34815"},{"key":"ref64","article-title":"Mova: Adapting mixture of vision experts to multimodal context","author":"Zong","year":"2024","journal-title":"arXiv preprint"}],"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\/11444921.pdf?arnumber=11444921","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:12:44Z","timestamp":1777529564000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444921\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00289","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}