{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T01:10:25Z","timestamp":1755825025024,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":5,"publisher":"ACM","funder":[{"name":"Shanghai Pujiang Program","award":["23PJ1421800"],"award-info":[{"award-number":["23PJ1421800"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3734537","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:29:43Z","timestamp":1750876183000},"page":"1964-1967","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Reproducibility Companion Paper: u-LLaVA: Unifying Multi-Modal Tasks via Large Language Model"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2428-0305","authenticated-orcid":false,"given":"Jinjin","family":"Xu","sequence":"first","affiliation":[{"name":"Bytedance, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0926-4454","authenticated-orcid":false,"given":"Xilu","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Surrey, Surrey, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7651-5081","authenticated-orcid":false,"given":"Liwu","family":"Xu","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9098-2105","authenticated-orcid":false,"given":"Yuzhe","family":"Yang","sequence":"additional","affiliation":[{"name":"OPPO AI Center, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9672-2562","authenticated-orcid":false,"given":"Xiang","family":"Li","sequence":"additional","affiliation":[{"name":"Baidu, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8685-4300","authenticated-orcid":false,"given":"Fanyi","family":"Wang","sequence":"additional","affiliation":[{"name":"HONOR, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0783-1868","authenticated-orcid":false,"given":"Yanchun","family":"Xie","sequence":"additional","affiliation":[{"name":"OPPO AI Center, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8320-9277","authenticated-orcid":false,"given":"Yi-Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"Bytedance, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3582-9997","authenticated-orcid":false,"given":"Yaqian","family":"Li","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8060-248X","authenticated-orcid":false,"given":"Yunfan","family":"Hu","sequence":"additional","affiliation":[{"name":"Amazon, Seattle, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Xing","author":"Chiang Wei-Lin","year":"2023","unstructured":"Wei-Lin Chiang, Zhuohan Li, Zi Lin, Ying Sheng, Zhanghao Wu, Hao Zhang, Lianmin Zheng, Siyuan Zhuang, Yonghao Zhuang, Joseph E. Gonzalez, Ion Stoica, and Eric P. Xing. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.502"},{"key":"e_1_3_2_1_4_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. Advances in neural information processing systems, Vol. 36 (2023), 34892--34916."},{"key":"e_1_3_2_1_5_1","volume-title":"u-llava: Unifying multi-modal tasks via large language model. arXiv preprint arXiv:2311.05348","author":"Xu Jinjin","year":"2023","unstructured":"Jinjin Xu, Liwu Xu, Yuzhe Yang, Xiang Li, Fanyi Wang, Yanchun Xie, Yi-Jie Huang, and Yaqian Li. 2023. u-llava: Unifying multi-modal tasks via large language model. arXiv preprint arXiv:2311.05348 (2023)."}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Chicago IL USA","acronym":"ICMR '25"},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3734537","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:06:57Z","timestamp":1755749217000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3734537"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":5,"alternative-id":["10.1145\/3731715.3734537","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3734537","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}