{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:14:27Z","timestamp":1765340067058,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755697","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:26:51Z","timestamp":1761377211000},"page":"4972-4981","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["From Captions to Rewards\n                    <scp>(CaReVL):<\/scp>\n                    Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6070-8470","authenticated-orcid":false,"given":"Muzhi","family":"Dai","sequence":"first","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9160-1918","authenticated-orcid":false,"given":"Jiashuo","family":"Sun","sequence":"additional","affiliation":[{"name":"Xiamen University, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7666-4020","authenticated-orcid":false,"given":"Zhiyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6458-5266","authenticated-orcid":false,"given":"Shixuan","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1860-0379","authenticated-orcid":false,"given":"Rui","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, Beijing, China and Northwestern Polytechnical University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0019-4197","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence (TeleAI), China Telecom, 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":"Technical Report: A Highly Capable Language Model Locally on Your Phone. arXiv:2404.14219 [cs.CL] https:\/\/arxiv.org\/abs\/2404.14219","author":"Abdin Marah","year":"2024","unstructured":"Marah Abdin, Jyoti Aneja, Hany Awadalla, et al., 2024. Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone. arXiv:2404.14219 [cs.CL] https:\/\/arxiv.org\/abs\/2404.14219"},{"key":"e_1_3_2_1_2_1","volume-title":"Emma Bou Hanna, et al","author":"Agrawal Pravesh","year":"2024","unstructured":"Pravesh Agrawal, Szymon Antoniak, Emma Bou Hanna, et al., 2024. Pixtral 12B. arXiv:2410.07073 [cs.CV] https:\/\/arxiv.org\/abs\/2410.07073"},{"key":"e_1_3_2_1_3_1","unstructured":"Anthropic. 2023. Claude 3.5: Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet"},{"key":"e_1_3_2_1_4_1","unstructured":"Jinze Bai Shuai Bai Shusheng Yang Shijie Wang Sinan Tan Peng Wang Junyang Lin Chang Zhou and Jingren Zhou. 2023. Qwen-VL: A Versatile Vision-Language Model for Understanding Localization Text Reading and Beyond. arXiv:2308.12966 [cs.CV] https:\/\/arxiv.org\/abs\/2308.12966"},{"key":"e_1_3_2_1_5_1","unstructured":"Yuntao Bai Andy Jones Kamal Ndousse Amanda Askell Anna Chen Nova DasSarma Dawn Drain Stanislav Fort Deep Ganguli Tom Henighan et al. 2022. Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)."},{"key":"e_1_3_2_1_6_1","volume-title":"MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Chen Dongping","year":"2024","unstructured":"Dongping Chen, Ruoxi Chen, Shilin Zhang, Yaochen Wang, Yinuo Liu, Huichi Zhou, Qihui Zhang, Yao Wan, Pan Zhou, and Lichao Sun. 2024a. MLLM-as-a-Judge: Assessing Multimodal LLM-as-a-Judge with Vision-Language Benchmark. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Liang Chen Yichi Zhang Shuhuai Ren Haozhe Zhao Zefan Cai Yuchi Wang Peiyi Wang Xiangdi Meng Tianyu Liu and Baobao Chang. 2024b. PCA-Bench: Evaluating Multimodal Large Language Models in Perception-Cognition-Action Chain. arXiv:2402.15527 [cs.CL] https:\/\/arxiv.org\/abs\/2402.15527","DOI":"10.18653\/v1\/2024.findings-acl.64"},{"key":"e_1_3_2_1_8_1","volume-title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. CoRR","author":"Chen Zhe","year":"2023","unstructured":"Zhe Chen, Jiannan Wu, Wenhai Wang, Weijie Su, Guo Chen, Sen Xing, Muyan Zhong, Qinglong Zhang, Xizhou Zhu, Lewei Lu, Bin Li, Ping Luo, Tong Lu, Yu Qiao, and Jifeng Dai. 2023. InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks. CoRR, Vol. abs\/2312.14238 (2023)."},{"key":"e_1_3_2_1_9_1","unstructured":"Paul Christiano Jan Leike Tom B. Brown Miljan Martic Shane Legg and Dario Amodei. 2023. Deep reinforcement learning from human preferences. arXiv:1706.03741 [stat.ML] https:\/\/arxiv.org\/abs\/1706.03741"},{"key":"e_1_3_2_1_10_1","unstructured":"Muzhi Dai Shixuan Liu and Qingyi Si. 2025a. Stable Reinforcement Learning for Efficient Reasoning. arXiv:2505.18086 [cs.AI] https:\/\/arxiv.org\/abs\/2505.18086"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Muzhi Dai Shixuan Liu Zhiyuan Zhao Junyu Gao Hao Sun and Xuelong Li. 2025b. Secure Tug-of-War (SecTOW): Iterative Defense-Attack Training with Reinforcement Learning for Multimodal Model Security. arXiv:2507.22037 [cs.CR] https:\/\/arxiv.org\/abs\/2507.22037","DOI":"10.1145\/3746027.3755236"},{"key":"e_1_3_2_1_12_1","unstructured":"Muzhi Dai Chenxu Yang and Qingyi Si. 2025c. S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models. arXiv:2505.07686 [cs.AI] https:\/\/arxiv.org\/abs\/2505.07686"},{"key":"e_1_3_2_1_13_1","volume-title":"NVLM: Open Frontier-Class Multimodal LLMs. CoRR","author":"Dai Wenliang","year":"2024","unstructured":"Wenliang Dai, Nayeon Lee, Boxin Wang, Zhuoling Yang, Zihan Liu, Jon Barker, Tuomas Rintamaki, Mohammad Shoeybi, Bryan Catanzaro, and Wei Ping. 2024. NVLM: Open Frontier-Class Multimodal LLMs. CoRR, Vol. abs\/2409.11402 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Jae Sung Park, et al","author":"Deitke Matt","year":"2024","unstructured":"Matt Deitke, Christopher Clark, Sangho Lee, Rohun Tripathi, Yue Yang, Jae Sung Park, et al., 2024. Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models. arXiv:2409.17146 [cs.CV] https:\/\/arxiv.org\/abs\/2409.17146"},{"key":"e_1_3_2_1_15_1","volume-title":"Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, and Ji-Rong Wen.","author":"Du Yifan","year":"2025","unstructured":"Yifan Du, Hangyu Guo, Kun Zhou, Wayne Xin Zhao, Jinpeng Wang, Chuyuan Wang, Mingchen Cai, Ruihua Song, and Ji-Rong Wen. 2025. What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning. arXiv:2311.01487 [cs.CV] https:\/\/arxiv.org\/abs\/2311.01487"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.26599\/TST.2019.9010029"},{"key":"e_1_3_2_1_17_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri et al. 2024. The Llama 3 Herd of Models. arXiv:2407.21783 [cs.AI] https:\/\/arxiv.org\/abs\/2407.21783"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.09.056"},{"key":"e_1_3_2_1_19_1","volume-title":"Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi.","author":"Lambert Nathan","year":"2024","unstructured":"Nathan Lambert, Valentina Pyatkin, Jacob Morrison, LJ Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, Noah A. Smith, and Hannaneh Hajishirzi. 2024. RewardBench: Evaluating Reward Models for Language Modeling. arXiv:2403.13787 [cs.LG]"},{"key":"e_1_3_2_1_20_1","unstructured":"Bo Li Yuanhan Zhang Dong Guo Renrui Zhang Feng Li Hao Zhang Kaichen Zhang Peiyuan Zhang Yanwei Li Ziwei Liu and Chunyuan Li. 2024c. LLaVA-OneVision: Easy Visual Task Transfer. arXiv:2408.03326 [cs.CV] https:\/\/arxiv.org\/abs\/2408.03326"},{"key":"e_1_3_2_1_21_1","unstructured":"Chunyuan Li Cliff Wong Sheng Zhang Naoto Usuyama Haotian Liu Jianwei Yang Tristan Naumann Hoifung Poon and Jianfeng Gao. 2023a. LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day. arXiv:2306.00890 [cs.CV] https:\/\/arxiv.org\/abs\/2306.00890"},{"key":"e_1_3_2_1_22_1","volume-title":"Lingpeng Kong, and Qi Liu.","author":"Li Lei","year":"2024","unstructured":"Lei Li, Yuancheng Wei, Zhihui Xie, Xuqing Yang, Yifan Song, Peiyi Wang, Chenxin An, Tianyu Liu, Sujian Li, Bill Yuchen Lin, Lingpeng Kong, and Qi Liu. 2024a. VLRewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models. arXiv:2411.17451 [cs.CV] https:\/\/arxiv.org\/abs\/2411.17451"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"crossref","unstructured":"Lei Li Zhihui Xie Mukai Li Shunian Chen Peiyi Wang Liang Chen Yazheng Yang Benyou Wang Lingpeng Kong and Qi Liu. 2024b. VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models Alignment. arXiv:2410.09421 [cs.CV] https:\/\/arxiv.org\/abs\/2410.09421","DOI":"10.18653\/v1\/2024.emnlp-main.358"},{"key":"e_1_3_2_1_24_1","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:2306.04387 [cs.CV] https:\/\/arxiv.org\/abs\/2306.04387"},{"key":"e_1_3_2_1_25_1","volume-title":"Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451","author":"Liu Chris Yuhao","year":"2024","unstructured":"Chris Yuhao Liu, Liang Zeng, Jiacai Liu, Rui Yan, Jujie He, Chaojie Wang, Shuicheng Yan, Yang Liu, and Yahui Zhou. 2024c. Skywork-reward: Bag of tricks for reward modeling in llms. arXiv preprint arXiv:2410.18451 (2024)."},{"key":"e_1_3_2_1_26_1","unstructured":"Fuxiao Liu Kevin Lin Linjie Li Jianfeng Wang Yaser Yacoob and Lijuan Wang. 2024b. Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning. arXiv:2306.14565 [cs.CV] https:\/\/arxiv.org\/abs\/2306.14565"},{"key":"e_1_3_2_1_27_1","unstructured":"Haotian Liu Chunyuan Li Yuheng Li and Yong Jae Lee. 2024a. Improved Baselines with Visual Instruction Tuning. arXiv:2310.03744 [cs.CV] https:\/\/arxiv.org\/abs\/2310.03744"},{"key":"e_1_3_2_1_28_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. arXiv:2304.08485 [cs.CV] https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"e_1_3_2_1_29_1","volume-title":"Yejin Choi, and Bill Yuchen Lin.","author":"Lu Yujie","year":"2024","unstructured":"Yujie Lu, Dongfu Jiang, Wenhu Chen, William Yang Wang, Yejin Choi, and Bill Yuchen Lin. 2024. WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences. arXiv:2406.11069 [cs.CV] https:\/\/arxiv.org\/abs\/2406.11069"},{"key":"e_1_3_2_1_30_1","unstructured":"OpenAI: Aaron Hurst Adam Lerer Adam P. Goucher Adam Perelman Aditya Ramesh et al. 2024a. GPT-4o System Card. arXiv:2410.21276 [cs.CL] https:\/\/arxiv.org\/abs\/2410.21276"},{"key":"e_1_3_2_1_31_1","unstructured":"OpenAI Josh Achiam Steven Adler Sandhini Agarwal et al. 2024b. GPT-4 Technical Report. arXiv:2303.08774 [cs.CL] https:\/\/arxiv.org\/abs\/2303.08774"},{"key":"e_1_3_2_1_32_1","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems Vol. 35 (2022) 27730-27744."},{"key":"e_1_3_2_1_33_1","first-page":"53728","article-title":"Direct preference optimization: Your language model is secretly a reward model","volume":"36","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. Advances in Neural Information Processing Systems, Vol. 36 (2023), 53728-53741.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40846-022-00696-6"},{"key":"e_1_3_2_1_35_1","unstructured":"Zhiqing Sun Sheng Shen Shengcao Cao Haotian Liu Chunyuan Li Yikang Shen Chuang Gan Liang-Yan Gui Yu-Xiong Wang Yiming Yang Kurt Keutzer and Trevor Darrell. 2023. Aligning Large Multimodal Models with Factually Augmented RLHF. arXiv:2309.14525 [cs.CV] https:\/\/arxiv.org\/abs\/2309.14525"},{"key":"e_1_3_2_1_36_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth Katie Millican et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_37_1","volume-title":"Ryan Burnell, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, et al., 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530 [cs.CL] https:\/\/arxiv.org\/abs\/2403.05530"},{"key":"e_1_3_2_1_38_1","unstructured":"Binghai Wang Rui Zheng Lu Chen Yan Liu Shihan Dou Caishuang Huang Wei Shen Senjie Jin Enyu Zhou Chenyu Shi Songyang Gao Nuo Xu Yuhao Zhou Xiaoran Fan Zhiheng Xi Jun Zhao Xiao Wang Tao Ji Hang Yan Lixing Shen Zhan Chen Tao Gui Qi Zhang Xipeng Qiu Xuanjing Huang Zuxuan Wu and Yu-Gang Jiang. 2024b. Secrets of RLHF in Large Language Models Part II: Reward Modeling. arXiv:2401.06080 [cs.AI] https:\/\/arxiv.org\/abs\/2401.06080"},{"key":"e_1_3_2_1_39_1","volume-title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. CoRR","author":"Wang Peng","year":"2024","unstructured":"Peng Wang, Shuai Bai, Sinan Tan, Shijie Wang, Zhihao Fan, Jinze Bai, Keqin Chen, Xuejing Liu, Jialin Wang, Wenbin Ge, Yang Fan, Kai Dang, Mengfei Du, Xuancheng Ren, Rui Men, Dayiheng Liu, Chang Zhou, Jingren Zhou, and Junyang Lin. 2024a. Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution. CoRR, Vol. abs\/2409.12191 (2024)."},{"key":"e_1_3_2_1_40_1","volume-title":"CogVLM: Visual Expert for Pretrained Language Models. CoRR","author":"Wang Weihan","year":"2023","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, Xixuan Song, Jiazheng Xu, Bin Xu, Juanzi Li, Yuxiao Dong, Ming Ding, and Jie Tang. 2023. CogVLM: Visual Expert for Pretrained Language Models. CoRR, Vol. abs\/2311.03079 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"LLaVA-Critic: Learning to Evaluate Multimodal Models. CoRR","author":"Xiong Tianyi","year":"2024","unstructured":"Tianyi Xiong, Xiyao Wang, Dong Guo, Qinghao Ye, Haoqi Fan, Quanquan Gu, Heng Huang, and Chunyuan Li. 2024. LLaVA-Critic: Learning to Evaluate Multimodal Models. CoRR, Vol. abs\/2410.02712 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Tianyu Yu Yuan Yao Haoye Zhang Taiwen He Yifeng Han Ganqu Cui Jinyi Hu Zhiyuan Liu Hai-Tao Zheng Maosong Sun and Tat-Seng Chua. 2024a. RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. arXiv:2312.00849 [cs.CL] https:\/\/arxiv.org\/abs\/2312.00849","DOI":"10.1109\/CVPR52733.2024.01310"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"crossref","unstructured":"Tianyu Yu Haoye Zhang Qiming Li Qixin Xu Yuan Yao Da Chen Xiaoman Lu Ganqu Cui Yunkai Dang Taiwen He Xiaocheng Feng Jun Song Bo Zheng Zhiyuan Liu Tat-Seng Chua and Maosong Sun. 2024b. RLAIF-V: Open-Source AI Feedback Leads to Super GPT-4V Trustworthiness. arXiv:2405.17220 [cs.CL] https:\/\/arxiv.org\/abs\/2405.17220","DOI":"10.1109\/CVPR52734.2025.01861"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Yuhang Zang Xiaoyi Dong Pan Zhang Yuhang Cao Ziyu Liu Shengyuan Ding Shenxi Wu Yubo Ma Haodong Duan Wenwei Zhang Kai Chen Dahua Lin and Jiaqi Wang. 2025. InternLM-XComposer2.5-Reward: A Simple Yet Effective Multi-Modal Reward Model. arXiv:2501.12368 [cs.CV] https:\/\/arxiv.org\/abs\/2501.12368","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2024.3404360"},{"key":"e_1_3_2_1_46_1","volume-title":"William Yang Wang, and Linda Ruth Petzold","author":"Zhang Xinlu","year":"2023","unstructured":"Xinlu Zhang, Yujie Lu, Weizhi Wang, An Yan, Jun Yan, Lianke Qin, Heng Wang, Xifeng Yan, William Yang Wang, and Linda Ruth Petzold. 2023. GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks. arXiv:2311.01361 [cs.CV] https:\/\/arxiv.org\/abs\/2311.01361"},{"key":"e_1_3_2_1_47_1","unstructured":"Yanzhe Zhang Ruiyi Zhang Jiuxiang Gu Yufan Zhou Nedim Lipka Diyi Yang and Tong Sun. 2024b. LLaVAR: Enhanced Visual Instruction Tuning for Text-Rich Image Understanding. arXiv:2306.17107 [cs.CV] https:\/\/arxiv.org\/abs\/2306.17107"},{"key":"e_1_3_2_1_48_1","volume-title":"SVIT: Scaling up Visual Instruction Tuning. arXiv:2307.04087 [cs.CV] https:\/\/arxiv.org\/abs\/2307.04087","author":"Zhao Bo","year":"2023","unstructured":"Bo Zhao, Boya Wu, Muyang He, and Tiejun Huang. 2023. SVIT: Scaling up Visual Instruction Tuning. arXiv:2307.04087 [cs.CV] https:\/\/arxiv.org\/abs\/2307.04087"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:54Z","timestamp":1765339794000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755697"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":48,"alternative-id":["10.1145\/3746027.3755697","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755697","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"}}]}}