{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,8]],"date-time":"2025-10-08T00:31:10Z","timestamp":1759883470183,"version":"build-2065373602"},"publisher-location":"New York, NY, USA","reference-count":19,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T00:00:00Z","timestamp":1746662400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022YFB4500300"],"award-info":[{"award-number":["2022YFB4500300"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271452"],"award-info":[{"award-number":["62271452"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,8]]},"DOI":"10.1145\/3701716.3718372","type":"proceedings-article","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T16:06:11Z","timestamp":1748016371000},"page":"3044-3048","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6400-2084","authenticated-orcid":false,"given":"Bin","family":"Chen","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1360-8309","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5108-0876","authenticated-orcid":false,"given":"Hongfei","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Chinese Academy of Sciences, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9746-351X","authenticated-orcid":false,"given":"Yizi","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7626-0162","authenticated-orcid":false,"given":"Hongyang","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, Zhejiang, China"}]}],"member":"320","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401184"},{"key":"e_1_3_2_1_2_1","volume-title":"Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966","author":"Bai J.","year":"2023","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., and Zhou, J. Qwen-vl: A frontier large vision-language model with versatile abilities. arXiv preprint arXiv:2308.12966 (2023)."},{"key":"e_1_3_2_1_3_1","volume-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 1, 2","author":"Bai J.","year":"2023","unstructured":"Bai, J., Bai, S., Yang, S., Wang, S., Tan, S., Wang, P., Lin, J., Zhou, C., and Zhou, J. Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond. arXiv preprint arXiv:2308.12966 1, 2 (2023), 3."},{"key":"e_1_3_2_1_4_1","unstructured":"Chaslot G. M. J.-B. C. Monte-carlo tree search."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"e_1_3_2_1_6_1","first-page":"8469","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess D.","year":"2023","unstructured":"Driess, D., Xia, F., Sajjadi, M. S., Lynch, C., Chowdhery, A., Ichter, B.,Wahid, A., Tompson, J., Vuong, Q., Yu, T., et al. Palm-e: an embodied multimodal language model. In Proceedings of the 40th International Conference on Machine Learning (2023), pp. 8469--8488."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"e_1_3_2_1_9_1","volume-title":"Visual instruction tuning. Advances in neural information processing systems 36","author":"Liu H.","year":"2024","unstructured":"Liu, H., Li, C., Wu, Q., and Lee, Y. J. Visual instruction tuning. Advances in neural information processing systems 36 (2024)."},{"key":"e_1_3_2_1_10_1","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu Z.","year":"2021","unstructured":"Liu, Z., Wang, Y., Han, K., Zhang, W., Ma, S., and Gao, W. Post-training quantization for vision transformer. Advances in Neural Information Processing Systems 34 (2021), 28092--28103.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10479-022-04834-w"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557670"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"e_1_3_2_1_14_1","volume-title":"Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191","author":"Wang P.","year":"2024","unstructured":"Wang, P., Bai, S., Tan, S., Wang, S., Fan, Z., Bai, J., Chen, K., Liu, X., Wang, J., Ge, W., et al. Qwen2-vl: Enhancing vision-language model's perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72920-1_22"},{"key":"e_1_3_2_1_16_1","first-page":"38087","volume-title":"International Conference on Machine Learning","author":"Xiao G.","year":"2023","unstructured":"Xiao, G., Lin, J., Seznec, M., Wu, H., Demouth, J., and Han, S. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning (2023), PMLR, pp. 38087--38099."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-17120-8_58"},{"key":"e_1_3_2_1_18_1","volume-title":"Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601","author":"Zhang D.","year":"2024","unstructured":"Zhang, D., Yu, Y., Dong, J., Li, C., Su, D., Chu, C., and Yu, D. Mm-llms: Recent advances in multimodal large language models. arXiv preprint arXiv:2401.13601 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358055"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Companion Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3718372","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3701716.3718372","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:51:38Z","timestamp":1759859498000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3701716.3718372"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,8]]},"references-count":19,"alternative-id":["10.1145\/3701716.3718372","10.1145\/3701716"],"URL":"https:\/\/doi.org\/10.1145\/3701716.3718372","relation":{},"subject":[],"published":{"date-parts":[[2025,5,8]]},"assertion":[{"value":"2025-05-23","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}