{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T05:05:03Z","timestamp":1750309503348,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":32,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306216,72074171,72374161"],"award-info":[{"award-number":["62306216,72074171,72374161"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Special Fund of Hubei Luojia Laboratory","award":["220100014"],"award-info":[{"award-number":["220100014"]}]},{"name":"Natural Science Foundation of Hubei Province of China","award":["2023AFB816"],"award-info":[{"award-number":["2023AFB816"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2042023kf0133"],"award-info":[{"award-number":["2042023kf0133"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681685","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"10735-10744","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-modal Auto-regressive Modeling via Visual Tokens"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7347-0648","authenticated-orcid":false,"given":"Tianshuo","family":"Peng","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0436-8446","authenticated-orcid":false,"given":"Zuchao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0542-2280","authenticated-orcid":false,"given":"Lefei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-0487","authenticated-orcid":false,"given":"Hai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0033-4150","authenticated-orcid":false,"given":"Ping","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-3448","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, Hubei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Alayrac Jean-Baptiste","year":"2022","unstructured":"Jean-Baptiste Alayrac, Jeff Donahue, Pauline Luc, Antoine Miech, Iain Barr, Yana Hasson, Karel Lenc, Arthur Mensch, Katherine Millican, Malcolm Reynolds, Roman Ring, Eliza Rutherford, Serkan Cabi, Tengda Han, Zhitao Gong, Sina Samangooei, Marianne Monteiro, Jacob L. Menick, Sebastian Borgeaud, Andy Brock, Aida Nematzadeh, Sahand Sharifzadeh, Mikolaj Binkowski, Ricardo Barreira, Oriol Vinyals, Andrew Zisserman, and Kar\u00e9n Simonyan. 2022. Flamingo: a Visual Language Model for Few-Shot Learning. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/960a172bc7fbf0177ccccbb411a7d800-Abstract-Conference.html"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.12966"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.00785"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.06500"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.11499"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.04790"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/S11263-018--1116-0"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2302.14045"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"e_1_3_2_1_11_1","unstructured":"IDEFICS. 2023. Introducing IDEFICS: An Open Reproduction of State-of-the-Art Visual Language Model. https:\/\/huggingface.co\/blog\/idefics."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de Las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. CoRR abs\/2310.06825 (2023). https:\/\/doi.org\/10.48550\/ARXIV.2310.06825 arXiv:2310.06825","DOI":"10.48550\/ARXIV.2310.06825"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2309.04669"},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning, ICML 2023","volume":"19742","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven C. H. Hoi. 2023. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models. In International Conference on Machine Learning, ICML 2023, 23--29 July 2023, Honolulu, Hawaii, USA (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730--19742. https:\/\/proceedings.mlr.press\/v202\/li23q.html"},{"key":"e_1_3_2_1_15_1","volume-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022","volume":"12900","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven C. H. Hoi. 2022. BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation. In International Conference on Machine Learning, ICML 2022, 17--23 July 2022, Baltimore, Maryland, USA (Proceedings of Machine Learning Research, Vol. 162), Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesv\u00e1ri, Gang Niu, and Sivan Sabato (Eds.). PMLR, 12888--12900. https:\/\/proceedings.mlr.press\/v162\/li22n.html"},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021","author":"Li Junnan","year":"2021","unstructured":"Junnan Li, Ramprasaath R. Selvaraju, Akhilesh Gotmare, Shafiq R. Joty, Caiming Xiong, and Steven Chu-Hong Hoi. 2021. Align before Fuse: Vision and Language Representation Learning with Momentum Distillation. In Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, NeurIPS 2021, December 6--14, 2021, virtual, Marc?Aurelio Ranzato, Alina Beygelzimer, Yann N. Dauphin, Percy Liang, and JenniferWortman Vaughan (Eds.). 9694--9705. https:\/\/proceedings.neurips.cc\/paper\/2021\/hash\/505259756244493872b7709a8a01b536-Abstract.html"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.15947"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2310.03744"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2307.06281"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.17172"},{"key":"e_1_3_2_1_23_1","volume-title":"Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Swaroop Mishra, Tanglin Xia, Liang Qiu, Kai-Wei Chang, Song-Chun Zhu, Oyvind Tafjord, Peter Clark, and Ashwin Kalyan. 2022. Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/11332b6b6cf4485b84afadb1352d3a9a-Abstract-Conference.html"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24","volume":"8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. In Proceedings of the 38th International Conference on Machine Learning, ICML 2021, 18--24 July 2021, Virtual Event (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763. http:\/\/proceedings.mlr.press\/v139\/radford21a.html"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.13286"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2307.05222"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2401.10208"},{"volume-title":"Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/vicuna.lmsys.org\/.","year":"2023","key":"e_1_3_2_1_29_1","unstructured":"Vicuna. 2023. Vicuna: An Open-Source Chatbot Impressing GPT-4 with 90%* ChatGPT Quality. https:\/\/vicuna.lmsys.org\/."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2304.14178"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2308.02490"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.09251"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681685","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681685","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:50Z","timestamp":1750295870000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681685"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":32,"alternative-id":["10.1145\/3664647.3681685","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681685","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"}}]}}