{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:18Z","timestamp":1765340058049,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","funder":[{"name":"Beijing Natural Science Foundation","award":["L247010"],"award-info":[{"award-number":["L247010"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755296","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"4039-4047","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["VL-DynaRefine: A Vision-Language Dynamic Refinement Approach for Visual Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7764-1666","authenticated-orcid":false,"given":"Jing","family":"Ma","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8550-7894","authenticated-orcid":false,"given":"Haochen","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5975-2135","authenticated-orcid":false,"given":"Zeyuan","family":"Zang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4798-4233","authenticated-orcid":false,"given":"Fangxiang","family":"Feng","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8762-2773","authenticated-orcid":false,"given":"Caixia","family":"Yuan","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7059-2723","authenticated-orcid":false,"given":"Lei","family":"Ren","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8046-0370","authenticated-orcid":false,"given":"Huixing","family":"Jiang","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0229-7198","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"Li Auto Inc., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0314-8951","authenticated-orcid":false,"given":"Xiaojie","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"unstructured":"Jean-Baptiste Alayrac Jeff Donahue Pauline Luc Antoine Miech Iain Barr Yana Hasson Karel Lenc Arthur Mensch Katherine Millican Malcolm Reynolds et al. 2022. Flamingo: a visual language model for few-shot learning. Advances in neural information processing systems Vol. 35 (2022) 23716-23736.","key":"e_1_3_2_1_2_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_3_1","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"e_1_3_2_1_4_1","first-page":"49250","volume-title":"Levine (Eds.)","volume":"36","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, DONGXU LI, Anthony Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale N Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Advances in Neural Information Processing Systems, A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36. Curran Associates, Inc., 49250-49267. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/9a6a435e75419a836fe47ab6793623e6-Paper-Conference.pdf"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_5_1","DOI":"10.1109\/TPAMI.2022.3210780"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_6_1","DOI":"10.1145\/3664647.3681082"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_7_1","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"e_1_3_2_1_8_1","volume-title":"Imagebind-llm: Multi-modality instruction tuning. arXiv preprint arXiv:2309.03905","author":"Han Jiaming","year":"2023","unstructured":"Jiaming Han, Renrui Zhang, Wenqi Shao, Peng Gao, Peng Xu, Han Xiao, Kaipeng Zhang, Chris Liu, Song Wen, Ziyu Guo, et al., 2023. Imagebind-llm: Multi-modality instruction tuning. arXiv preprint arXiv:2309.03905 (2023)."},{"key":"e_1_3_2_1_9_1","volume-title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models. In Advances in Neural Information Processing Systems","author":"Hu Yushi","year":"2024","unstructured":"Yushi Hu, Weijia Shi, Xingyu Fu, Dan Roth, Mari Ostendorf, Luke Zettlemoyer, Noah A Smith, and Ranjay Krishna. 2024. Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 139348-139379. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2024\/file\/fb82011040977c7712409fbdb5456647-Paper-Conference.pdf"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_10_1","DOI":"10.1109\/CVPR.2019.00686"},{"unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024).","key":"e_1_3_2_1_11_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_12_1","DOI":"10.1109\/CVPR.2017.215"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_13_1","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_1_14_1","volume-title":"HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning. In European Conference on Computer Vision. Springer, 132-149","author":"Ke Fucai","year":"2024","unstructured":"Fucai Ke, Zhixi Cai, Simindokht Jahangard, Weiqing Wang, Pari Delir Haghighi, and Hamid Rezatofighi. 2024. HYDRA: A Hyper Agent for Dynamic Compositional Visual Reasoning. In European Conference on Computer Vision. Springer, 132-149."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_15_1","DOI":"10.18653\/v1\/2024.findings-emnlp.483"},{"key":"e_1_3_2_1_16_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023a. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730-19742."},{"key":"e_1_3_2_1_17_1","volume-title":"A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. arXiv preprint arXiv:2306.04387","author":"Li Lei","year":"2023","unstructured":"Lei Li, Yuwei Yin, Shicheng Li, Liang Chen, Peiyi Wang, Shuhuai Ren, Mukai Li, Yazheng Yang, Jingjing Xu, Xu Sun, Lingpeng Kong, and Qi Liu. 2023b. M^3IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. arXiv preprint arXiv:2306.04387 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_18_1","DOI":"10.1109\/CVPR52688.2022.01069"},{"unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning.","key":"e_1_3_2_1_19_1"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_20_1","DOI":"10.1109\/CVPR.2019.00431"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_21_1","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_1_22_1","first-page":"72983","article-title":"Scaling open-vocabulary object detection","volume":"36","author":"Minderer Matthias","year":"2023","unstructured":"Matthias Minderer, Alexey Gritsenko, and Neil Houlsby. 2023. Scaling open-vocabulary object detection. Advances in Neural Information Processing Systems, Vol. 36 (2023), 72983-73007.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","volume-title":"Simple Open-Vocabulary Object Detection. In European Conference on Computer Vision. 728-755","author":"Minderer Matthias","year":"2022","unstructured":"Matthias Minderer, Alexey Gritsenko, Austin Stone, Maxim Neumann, Dirk Weissenborn, Alexey Dosovitskiy, Aravindh Mahendran, Anurag Arnab, Mostafa Dehghani, Zhuoran Shen, et al., 2022. Simple Open-Vocabulary Object Detection. In European Conference on Computer Vision. 728-755."},{"key":"e_1_3_2_1_24_1","volume-title":"Kosmos-2: Grounding Multimodal Large Language Models to the World. ArXiv","author":"Peng Zhiliang","year":"2023","unstructured":"Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. 2023. Kosmos-2: Grounding Multimodal Large Language Models to the World. ArXiv, Vol. abs\/2306 (2023)."},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_25_1","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!","author":"Su Yixuan","year":"2023","unstructured":"Yixuan Su, Tian Lan, Huayang Li, Jialu Xu, Yan Wang, and Deng Cai. 2023. PandaGPT: One Model To Instruction-Follow Them All. In Proceedings of the 1st Workshop on Taming Large Language Models: Controllability in the era of Interactive Assistants!, Devamanyu Hazarika, Xiangru Robert Tang, and Di Jin (Eds.). Association for Computational Linguistics, Prague, Czech Republic, 11-23. https:\/\/aclanthology.org\/2023.tllm-1.2\/"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_27_1","DOI":"10.18653\/v1\/2022.acl-long.357"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_28_1","DOI":"10.18653\/v1\/2023.acl-short.65"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_29_1","DOI":"10.1109\/ICCV51070.2023.01092"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_30_1","DOI":"10.1145\/3664647.3681010"},{"key":"e_1_3_2_1_31_1","first-page":"61501","article-title":"Visionllm: Large language model is also an open-ended decoder for vision-centric tasks","volume":"36","author":"Wang Wenhai","year":"2023","unstructured":"Wenhai Wang, Zhe Chen, Xiaokang Chen, Jiannan Wu, Xizhou Zhu, Gang Zeng, Ping Luo, Tong Lu, Jie Zhou, Yu Qiao, et al., 2023. Visionllm: Large language model is also an open-ended decoder for vision-centric tasks. Advances in Neural Information Processing Systems, Vol. 36 (2023), 61501-61513.","journal-title":"Advances in Neural Information Processing Systems"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_32_1","DOI":"10.18653\/v1\/2024.findings-emnlp.575"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_33_1","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KRLUvxh8uaX","author":"Yuksekgonul Mert","year":"2023","unstructured":"Mert Yuksekgonul, Federico Bianchi, Pratyusha Kalluri, Dan Jurafsky, and James Zou. 2023. When and why Vision-Language Models behave like Bags-of-Words, and what to do about it?. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=KRLUvxh8uaX"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_35_1","DOI":"10.1109\/CVPR.2019.00688"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_36_1","DOI":"10.1109\/CVPR.2019.00546"},{"doi-asserted-by":"publisher","key":"e_1_3_2_1_37_1","DOI":"10.18653\/v1\/2024.findings-acl.49"}],"event":{"sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"acronym":"MM '25","name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755296","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:24Z","timestamp":1765339764000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755296"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":37,"alternative-id":["10.1145\/3746027.3755296","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755296","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}