{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T09:08:33Z","timestamp":1765357713492,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":53,"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":"the Science and Technology Planning Project of Guangdong Province","award":["2020B0101100002"],"award-info":[{"award-number":["2020B0101100002"]}]},{"name":"Guangdong Provincial Fund for Basic and Applied Basic Research?Regional Joint Fund Project (Key Project)","award":["2023B1515120078"],"award-info":[{"award-number":["2023B1515120078"]}]},{"name":"the Fundamental Research Funds for the Central Universities, South China University of Technology","award":["x2rjD2240100"],"award-info":[{"award-number":["x2rjD2240100"]}]},{"name":"Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project","award":["2024B1515040010"],"award-info":[{"award-number":["2024B1515040010"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076100"],"award-info":[{"award-number":["62076100"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the China Computer Federation (CCF)-Zhipu AI Large Model Fund"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681590","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"8209-8218","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Learning to Correction: Explainable Feedback Generation for Visual Commonsense Reasoning Distractor"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8064-1577","authenticated-orcid":false,"given":"Jiali","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3148-139X","authenticated-orcid":false,"given":"Xusen","family":"Hei","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6423-123X","authenticated-orcid":false,"given":"Yuqi","family":"Xue","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-1576-3341","authenticated-orcid":false,"given":"Yuancheng","family":"Wei","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-7879","authenticated-orcid":false,"given":"Jiayuan","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1767-789X","authenticated-orcid":false,"given":"Yi","family":"Cai","sequence":"additional","affiliation":[{"name":"South China University of Technology, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"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":"Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR","author":"Bai Jinze","year":"2023","unstructured":"Jinze Bai, Shuai Bai, Shusheng Yang, Shijie Wang, Sinan Tan, Peng Wang, Junyang Lin, Chang Zhou, and Jingren Zhou. 2023. Qwen-VL: A Frontier Large Vision-Language Model with Versatile Abilities. CoRR, Vol. abs\/2308.12966 (2023)."},{"key":"e_1_3_2_1_2_1","unstructured":"Benjamin S Bloom Max D Engelhart Edward J Furst Walker H Hill David R Krathwohl et al. 1956. Taxonomy of educational objectives: The classification of educational goals. Handbook 1: Cognitive domain. Longman New York."},{"key":"e_1_3_2_1_3_1","volume-title":"Gregory P. Meyer, Yuning Chai, Dennis Park, and Yong Jae Lee.","author":"Cai Mu","year":"2023","unstructured":"Mu Cai, Haotian Liu, Siva Karthik Mustikovela, Gregory P. Meyer, Yuning Chai, Dennis Park, and Yong Jae Lee. 2023. Making Large Multimodal Models Understand Arbitrary Visual Prompts. CoRR, Vol. abs\/2312.00784 (2023)."},{"volume-title":"Proc. of AAAI","author":"Chen Delong","key":"e_1_3_2_1_4_1","unstructured":"Delong Chen, Jianfeng Liu, Wenliang Dai, and Baoyuan Wang. 2024. Visual Instruction Tuning with Polite Flamingo. In Proc. of AAAI, Michael J. Wooldridge, Jennifer G. Dy, and Sriraam Natarajan (Eds.). AAAI Press, 17745--17753."},{"key":"e_1_3_2_1_5_1","volume-title":"Microsoft COCO Captions: Data Collection and Evaluation Server. CoRR","author":"Chen Xinlei","year":"2015","unstructured":"Xinlei Chen, Hao Fang, Tsung-Yi Lin, Ramakrishna Vedantam, Saurabh Gupta, Piotr Doll\u00e1r, and C. Lawrence Zitnick. 2015. Microsoft COCO Captions: Data Collection and Evaluation Server. CoRR, Vol. abs\/1504.00325 (2015)."},{"key":"e_1_3_2_1_6_1","volume-title":"GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs. CoRR","author":"Chen Zhenfang","year":"2023","unstructured":"Zhenfang Chen, Rui Sun, Wenjun Liu, Yining Hong, and Chuang Gan. 2023. GENOME: GenerativE Neuro-symbOlic visual reasoning by growing and reusing ModulEs. CoRR, Vol. abs\/2311.04901 (2023)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevPhysEducRes.15.020134"},{"key":"e_1_3_2_1_8_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven C. H. 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 C. H. Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. In Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_1_9_1","volume-title":"Visual Dialog. In Proc. of CVPR. IEEE Computer Society, 1080--1089","author":"Das Abhishek","year":"2017","unstructured":"Abhishek Das, Satwik Kottur, Khushi Gupta, Avi Singh, Deshraj Yadav, Jos\u00e9 M. F. Moura, Devi Parikh, and Dhruv Batra. 2017. Visual Dialog. In Proc. of CVPR. IEEE Computer Society, 1080--1089."},{"volume-title":"Proc. of ACL Workshop. 376--380","author":"Michael","key":"e_1_3_2_1_10_1","unstructured":"Michael J. Denkowski and Alon Lavie. 2014. Meteor Universal: Language Specific Translation Evaluation for Any Target Language. In Proc. of ACL Workshop. 376--380."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.66"},{"key":"e_1_3_2_1_12_1","volume-title":"Proc. of ICLR. 1--12","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In Proc. of ICLR. 1--12."},{"key":"e_1_3_2_1_13_1","volume-title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling. In Proc. of ACL","author":"Du Zhengxiao","year":"2022","unstructured":"Zhengxiao Du, Yujie Qian, Xiao Liu, Ming Ding, Jiezhong Qiu, Zhilin Yang, and Jie Tang. 2022. GLM: General Language Model Pretraining with Autoregressive Blank Infilling. In Proc. of ACL, Smaranda Muresan, Preslav Nakov, and Aline Villavicencio (Eds.). Association for Computational Linguistics, 320--335."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.75"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01436"},{"key":"e_1_3_2_1_17_1","volume-title":"CogAgent: A Visual Language Model for GUI Agents. CoRR","author":"Hong Wenyi","year":"2023","unstructured":"Wenyi Hong, Weihan Wang, Qingsong Lv, Jiazheng Xu, Wenmeng Yu, Junhui Ji, Yan Wang, Zihan Wang, Yuxuan Zhang, Juanzi Li, Bin Xu, Yuxiao Dong, Ming Ding, and Jie Tang. 2023. CogAgent: A Visual Language Model for GUI Agents. CoRR, Vol. abs\/2312.08914 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Proc. of ICLR. OpenReview.net.","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 Proc. of ICLR. OpenReview.net."},{"key":"e_1_3_2_1_19_1","volume-title":"Kingma and Jimmy Ba","author":"Diederik","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A Method for Stochastic Optimization. In Proc. of ICLR."},{"key":"e_1_3_2_1_20_1","volume-title":"Girshick","author":"Kirillov Alexander","year":"2023","unstructured":"Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chlo\u00e9 Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Doll\u00e1r, and Ross B. Girshick. 2023. Segment Anything. In Proc. of ICCV. IEEE, 3992--4003."},{"key":"e_1_3_2_1_21_1","volume-title":"CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding. CoRR","author":"Li Junyan","year":"2023","unstructured":"Junyan Li, Delin Chen, Yining Hong, Zhenfang Chen, Peihao Chen, Yikang Shen, and Chuang Gan. 2023. CoVLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding. CoRR, Vol. abs\/2311.03354 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Hoi","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 Proc. of ICML (Proceedings of Machine Learning Research, Vol. 202), Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett (Eds.). PMLR, 19730--19742."},{"key":"e_1_3_2_1_23_1","volume-title":"2023 d. M(^mbox3)IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. CoRR","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. 2023 d. M(^mbox3)IT: A Large-Scale Dataset towards Multi-Modal Multilingual Instruction Tuning. CoRR, Vol. abs\/2306.04387 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.601"},{"key":"e_1_3_2_1_25_1","volume-title":"Proc. of ACL Workshop. 74--81","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Proc. of ACL Workshop. 74--81."},{"key":"e_1_3_2_1_26_1","volume-title":"Aligning Large Multi-Modal Model with Robust Instruction Tuning. CoRR","author":"Liu Fuxiao","year":"2023","unstructured":"Fuxiao Liu, Kevin Lin, Linjie Li, Jianfeng Wang, Yaser Yacoob, and Lijuan Wang. 2023. Aligning Large Multi-Modal Model with Robust Instruction Tuning. CoRR, Vol. abs\/2306.14565 (2023)."},{"key":"e_1_3_2_1_27_1","volume-title":"Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.).","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_1_28_1","volume-title":"Proc. of NeurIPS","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 Proc. of NeurIPS 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.)."},{"key":"e_1_3_2_1_29_1","volume-title":"Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.).","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. 2023. Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models. In Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"e_1_3_2_1_31_1","volume-title":"Murchison","author":"Carl","year":"1930","unstructured":"Carl Ed Murchison. 1930. A history of psychology in autobiography Vol. I.Russell & Russell\/Atheneum Publishers."},{"key":"e_1_3_2_1_33_1","volume-title":"Proc. of ACL. 311--318","author":"Papineni Kishore","year":"2002","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a Method for Automatic Evaluation of Machine Translation. In Proc. of ACL. 311--318."},{"key":"e_1_3_2_1_34_1","volume-title":"Proc. of ICML (Proceedings of Machine Learning Research","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 Proc. of ICML (Proceedings of Machine Learning Research, Vol. 139), Marina Meila and Tong Zhang (Eds.). PMLR, 8748--8763."},{"key":"e_1_3_2_1_35_1","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei Ilya Sutskever et al. 2019. Language models are unsupervised multitask learners. OpenAI blog Vol. 1 8 (2019) 9."},{"key":"e_1_3_2_1_36_1","volume-title":"Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.).","author":"Rafailov Rafael","year":"2023","unstructured":"Rafael Rafailov, Archit Sharma, Eric Mitchell, Christopher D. Manning, Stefano Ermon, and Chelsea Finn. 2023. Direct Preference Optimization: Your Language Model is Secretly a Reward Model. In Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00814"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"e_1_3_2_1_41_1","volume-title":"What Makes for Good Visual Tokenizers for Large Language Models? CoRR","author":"Wang Guangzhi","year":"2023","unstructured":"Guangzhi Wang, Yixiao Ge, Xiaohan Ding, Mohan S. Kankanhalli, and Ying Shan. 2023. What Makes for Good Visual Tokenizers for Large Language Models? CoRR, Vol. abs\/2305.12223 (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3379900"},{"key":"e_1_3_2_1_43_1","volume-title":"Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs. CoRR","author":"Xuan Shiyu","year":"2023","unstructured":"Shiyu Xuan, Qingpei Guo, Ming Yang, and Shiliang Zhang. 2023. Pink: Unveiling the Power of Referential Comprehension for Multi-modal LLMs. CoRR, Vol. abs\/2310.00582 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01054"},{"key":"e_1_3_2_1_45_1","volume-title":"Ziniu Hu, Nanyun Peng, and Kai-Wei Chang.","author":"Yin Da","year":"2021","unstructured":"Da Yin, Liunian Harold Li, Ziniu Hu, Nanyun Peng, and Kai-Wei Chang. 2021. Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning. In Proc. of EMNLP, Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih (Eds.). Association for Computational Linguistics, 2115--2129."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"key":"e_1_3_2_1_47_1","volume-title":"Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants. CoRR","author":"Yu Tianyu","year":"2023","unstructured":"Tianyu Yu, Jinyi Hu, Yuan Yao, Haoye Zhang, Yue Zhao, Chongyi Wang, Shan Wang, Yinxv Pan, Jiao Xue, Dahai Li, Zhiyuan Liu, Hai-Tao Zheng, and Maosong Sun. 2023. Reformulating Vision-Language Foundation Models and Datasets Towards Universal Multimodal Assistants. CoRR, Vol. abs\/2310.00653 (2023)."},{"key":"e_1_3_2_1_48_1","volume-title":"Proc. of COLING, Nicoletta Calzolari, Min-Yen Kan, V\u00e9ronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, 759--772","author":"Yuan Li","year":"2024","unstructured":"Li Yuan, Yi Cai, Haopeng Ren, and Jiexin Wang. 2024. A Logical Pattern Memory Pre-trained Model for Entailment Tree Generation. In Proc. of COLING, Nicoletta Calzolari, Min-Yen Kan, V\u00e9ronique Hoste, Alessandro Lenci, Sakriani Sakti, and Nianwen Xue (Eds.). ELRA and ICCL, 759--772."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"e_1_3_2_1_50_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona T. Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. OPT: Open Pre-trained Transformer Language Models. CoRR, Vol. abs\/2205.01068 (2022)."},{"key":"e_1_3_2_1_51_1","volume-title":"GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest. CoRR","author":"Zhang Shilong","year":"2023","unstructured":"Shilong Zhang, Peize Sun, Shoufa Chen, Min Xiao, Wenqi Shao, Wenwei Zhang, Kai Chen, and Ping Luo. 2023. GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest. CoRR, Vol. abs\/2307.03601 (2023)."},{"key":"e_1_3_2_1_52_1","volume-title":"Proc. of ICLR. OpenReview.net.","author":"Zhang Tianyi","year":"2020","unstructured":"Tianyi Zhang, Varsha Kishore, Felix Wu, Kilian Q. Weinberger, and Yoav Artzi. 2020. BERTScore: Evaluating Text Generation with BERT. In Proc. of ICLR. OpenReview.net."},{"key":"e_1_3_2_1_53_1","volume-title":"Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.).","author":"Zheng Ge","year":"2023","unstructured":"Ge Zheng, Bin Yang, Jiajin Tang, Hong-Yu Zhou, and Sibei Yang. 2023. DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models. In Proc. of NeurIPS, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.)."},{"key":"e_1_3_2_1_54_1","volume-title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. CoRR","author":"Zhu Deyao","year":"2023","unstructured":"Deyao Zhu, Jun Chen, Xiaoqian Shen, Xiang Li, and Mohamed Elhoseiny. 2023. MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models. CoRR, Vol. abs\/2304.10592 (2023)."}],"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\/3664647.3681590","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681590","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681590"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":53,"alternative-id":["10.1145\/3664647.3681590","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681590","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"}}]}}