{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:12:16Z","timestamp":1785543136408,"version":"3.56.0"},"publisher-location":"New York, NY, USA","reference-count":9,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Google Research","award":["G222897"],"award-info":[{"award-number":["G222897"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3689177","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"11294-11295","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multimodal Large Language Models and Tunings: Vision, Language, Sensors, Audio, and Beyond"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1948-6819","authenticated-orcid":false,"given":"Soyeon Caren","family":"Han","sequence":"first","affiliation":[{"name":"University of Melbourne, Melbourne, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4910-5925","authenticated-orcid":false,"given":"Feiqi","family":"Cao","sequence":"additional","affiliation":[{"name":"University of Sydney, University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3371-8628","authenticated-orcid":false,"given":"Josiah","family":"Poon","sequence":"additional","affiliation":[{"name":"University of Sydney, Sydney, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3831-9706","authenticated-orcid":false,"given":"Roberto","family":"Navigli","sequence":"additional","affiliation":[{"name":"Sapienza University of Rome, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Efros","author":"Brooks Tim","year":"2023","unstructured":"Tim Brooks, Aleksander Holynski, and Alexei A. Efros. 2023. InstructPix2Pix: Learning to Follow Image Editing Instructions. arXiv:2211.09800 [cs.CV]"},{"key":"e_1_3_2_1_2_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arXiv:2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_3_1","unstructured":"Tim Dettmers Artidoro Pagnoni Ari Holtzman and Luke Zettlemoyer. 2023. QLoRA: Efficient Finetuning of Quantized LLMs. arXiv:2305.14314 [cs.LG]"},{"key":"e_1_3_2_1_4_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=nZeVKeeFYf9","author":"Hu Edward J","year":"2022","unstructured":"Edward J Hu, yelong shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=nZeVKeeFYf9"},{"key":"e_1_3_2_1_5_1","unstructured":"Junnan Li Dongxu Li Silvio Savarese and Steven Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. arXiv:2301.12597 [cs.CV]"},{"key":"e_1_3_2_1_6_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. In NeurIPS."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022"},{"key":"e_1_3_2_1_8_1","unstructured":"OpenAI. 2023. GPT-4V(ision) System Card."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3689177","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3689177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:29Z","timestamp":1750295849000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3689177"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":9,"alternative-id":["10.1145\/3664647.3689177","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3689177","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}