{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T23:37:52Z","timestamp":1775173072716,"version":"3.50.1"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R & D Program of China","award":["2022ZD0160101"],"award-info":[{"award-number":["2022ZD0160101"]}]},{"name":"National Key R & D Program of China","award":["2022ZD0161000"],"award-info":[{"award-number":["2022ZD0161000"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1109\/tbdata.2025.3536930","type":"journal-article","created":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:23:41Z","timestamp":1738265021000},"page":"933-947","source":"Crossref","is-referenced-by-count":2,"title":["TinyLVLM-eHub: Towards Comprehensive and Efficient Evaluation for Large Vision-Language Models"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3781-4086","authenticated-orcid":false,"given":"Wenqi","family":"Shao","sequence":"first","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meng","family":"Lei","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yutao","family":"Hu","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7881-712X","authenticated-orcid":false,"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Xu","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6105-6532","authenticated-orcid":false,"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0920-3539","authenticated-orcid":false,"given":"Fanqing","family":"Meng","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2664-7975","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2567","authenticated-orcid":false,"given":"Yu","family":"Qiao","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"OpenGVLab, Shanghai AI Laboratory, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref2","article-title":"Otter: A multi-modal model with in-context instruction tuning","author":"Li","year":"2023"},{"key":"ref3","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref4","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref5","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023"},{"key":"ref6","article-title":"Med-flamingo: A multimodal medical few-shot learner","author":"Moor","year":"2023"},{"key":"ref7","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023"},{"key":"ref8","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"ref9","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"ref10","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref11","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref13","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref14","article-title":"Gemini","year":"2024"},{"key":"ref15","article-title":"What makes for good visual tokenizers for large language models","author":"Wang","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3507000"},{"key":"ref17","article-title":"MIMIC-IT: Multi-modal in-context instruction tuning","author":"Li","year":"2023"},{"key":"ref18","article-title":"MME: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref20","article-title":"SEED-bench: Benchmarking multimodal LLMs with generative comprehension","author":"Li","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref22","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref23","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref24","article-title":"mPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref25","article-title":"Transfer visual prompt generator across LLMs","author":"Zhang","year":"2023"},{"key":"ref26","article-title":"PandaGPT: One model to instruction-follow them all","author":"Su","year":"2023"},{"key":"ref27","article-title":"Bard","year":"2023"},{"key":"ref28","article-title":"Claude","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.133"},{"key":"ref31","article-title":"LAMM: Language-assisted multi-modal instruction-tuning dataset, framework, and benchmark","author":"Yin","year":"2023"},{"key":"ref32","article-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"ref33","article-title":"OpenFlamingo v2","author":"Anas","year":"2023"},{"key":"ref34","article-title":"OFASys: A multi-modal multi-task learning system for building generalist models","author":"Bai","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00886"},{"key":"ref36","article-title":"Judging LLM-as-a-judge with MT-bench and chatbot arena","author":"Zheng","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref38","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref41","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.07.008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2014.03.023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.76"},{"key":"ref50","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01393"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00251"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref62","article-title":"IconQA: A new benchmark for abstract diagram understanding and visual language reasoning","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Track Datasets Benchmarks","author":"Lu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00566"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00247"},{"key":"ref65","first-page":"2507","article-title":"Learn to explain: Multimodal reasoning via thought chains for science question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/1866029.1866080"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11003987\/10858438.pdf?arnumber=10858438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T19:37:39Z","timestamp":1747337859000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10858438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":66,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2025.3536930","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}