{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:39:40Z","timestamp":1783823980610,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":49,"publisher":"ACM","funder":[{"name":"This work was supported by the National Natural Science Foundation of China","award":["62225112"],"award-info":[{"award-number":["62225112"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3758207","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T07:39:06Z","timestamp":1761377946000},"page":"12690-12697","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["GOBench: Benchmarking Geometric Optics Generation and Understanding of MLLMs"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9145-3829","authenticated-orcid":false,"given":"Xiaorong","family":"Zhu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2623-4756","authenticated-orcid":false,"given":"Ziheng","family":"Jia","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9890-2698","authenticated-orcid":false,"given":"Jiarui","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1313-9451","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3052-4177","authenticated-orcid":false,"given":"Haodong","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5693-0416","authenticated-orcid":false,"given":"Xiongkuo","family":"Min","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1714-3206","authenticated-orcid":false,"given":"Jia","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7247-7938","authenticated-orcid":false,"given":"Zicheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8165-9322","authenticated-orcid":false,"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China and Shanghai AI Laboratory, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection. arXiv preprint arXiv:2411.10918","author":"Abshari Danial","year":"2024","unstructured":"Danial Abshari, Chenglong Fu, and Meera Sridhar. 2024. LLM-assisted Physical Invariant Extraction for Cyber-Physical Systems Anomaly Detection. arXiv preprint arXiv:2411.10918 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"e_1_3_2_1_3_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247693"},{"key":"e_1_3_2_1_5_1","unstructured":"James Betker Gabriel Goh Li Jing Tim Brooks Jianfeng Wang Linjie Li Long Ouyang Juntang Zhuang Joyce Lee Yufei Guo et al. 2023. Improving image generation with better captions. Computer Science. https:\/\/cdn. openai. com\/papers\/dall-e-3. pdf Vol. 2 3 (2023) 8."},{"key":"e_1_3_2_1_6_1","unstructured":"Xiao Bi Deli Chen Guanting Chen Shanhuang Chen Damai Dai Chengqi Deng Honghui Ding Kai Dong Qiushi Du Zhe Fu et al. 2024. Deepseek llm: Scaling open-source language models with longtermism. arXiv preprint arXiv:2401.02954 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Multi-modal generative ai: Multi-modal llm, diffusion and beyond. arXiv preprint arXiv:2409.14993","author":"Chen Hong","year":"2024","unstructured":"Hong Chen, Xin Wang, Yuwei Zhou, Bin Huang, Yipeng Zhang, Wei Feng, Houlun Chen, Zeyang Zhang, Siao Tang, and Wenwu Zhu. 2024b. Multi-modal generative ai: Multi-modal llm, diffusion and beyond. arXiv preprint arXiv:2409.14993 (2024)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Zhe Chen Weiyun Wang Hao Tian Shenglong Ye Zhangwei Gao Erfei Cui Wenwen Tong Kongzhi Hu Jiapeng Luo Zheng Ma Ji Ma Jiaqi Wang Xiaoyi Dong Hang Yan Hewei Guo Conghui He Botian Shi Zhenjiang Jin Chao Xu Bin Wang Xingjian Wei Wei Li Wenjian Zhang Bo Zhang Pinlong Cai Licheng Wen Xiangchao Yan Min Dou Lewei Lu Xizhou Zhu Tong Lu Dahua Lin Yu Qiao Jifeng Dai and Wenhai Wang. 2024a. How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites. arXiv:2404.16821 [cs.CV]","DOI":"10.1007\/s11432-024-4231-5"},{"key":"e_1_3_2_1_9_1","volume-title":"Llmphy: Complex physical reasoning using large language models and world models. arXiv preprint arXiv:2411.08027","author":"Cherian Anoop","year":"2024","unstructured":"Anoop Cherian, Radu Corcodel, Siddarth Jain, and Diego Romeres. 2024. Llmphy: Complex physical reasoning using large language models and world models. arXiv preprint arXiv:2411.08027 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Artificial intelligence as a general-purpose technology: an historical perspective","author":"Crafts Nicholas","unstructured":"Nicholas Crafts. 2021. Artificial intelligence as a general-purpose technology: an historical perspective. University of Sussex (2021)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"e_1_3_2_1_12_1","volume-title":"European Conference on Computer Vision. Springer, 148-166","author":"Fu Xingyu","year":"2024","unstructured":"Xingyu Fu, Yushi Hu, Bangzheng Li, Yu Feng, Haoyu Wang, Xudong Lin, Dan Roth, Noah A Smith, Wei-Chiu Ma, and Ranjay Krishna. 2024. Blink: Multimodal large language models can see but not perceive. In European Conference on Computer Vision. Springer, 148-166."},{"key":"e_1_3_2_1_13_1","volume-title":"Muzammal Naseer, Salman Khan, and Peter Wonka.","author":"Gani Hanan","year":"2023","unstructured":"Hanan Gani, Shariq Farooq Bhat, Muzammal Naseer, Salman Khan, and Peter Wonka. 2023. Llm blueprint: Enabling text-to-image generation with complex and detailed prompts. arXiv preprint arXiv:2310.10640 (2023)."},{"key":"e_1_3_2_1_14_1","unstructured":"Yu Gu Kai Zhang Yuting Ning Boyuan Zheng Boyu Gou Tianci Xue Cheng Chang Sanjari Srivastava Yanan Xie Peng Qi et al. 2024. Is your llm secretly a world model of the internet? model-based planning for web agents. arXiv preprint arXiv:2411.06559 (2024)."},{"key":"e_1_3_2_1_15_1","unstructured":"ANDR\u00c9 GUIDETTI. 2019. Artificial intelligence as general purpose technology: an empirical and applied analysis of its perception. (2019)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714933"},{"key":"e_1_3_2_1_17_1","unstructured":"Wenyi Hong Weihan Wang Ming Ding Wenmeng Yu Qingsong Lv Yan Wang Yean Cheng Shiyu Huang Junhui Ji Zhao Xue et al. 2024. Cogvlm2: Visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions. arXiv preprint arXiv:2411.02394","author":"Hsu Hao-Yu","year":"2024","unstructured":"Hao-Yu Hsu, Zhi-Hao Lin, Albert Zhai, Hongchi Xia, and Shenlong Wang. 2024. AutoVFX: Physically Realistic Video Editing from Natural Language Instructions. arXiv preprint arXiv:2411.02394 (2024)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589335.3648307"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00494"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"e_1_3_2_1_22_1","volume-title":"LLM-Assisted Visual Analytics: Opportunities and Challenges. arXiv preprint arXiv:2409.02691","author":"Hutchinson Maeve","year":"2024","unstructured":"Maeve Hutchinson, Radu Jianu, Aidan Slingsby, and Pranava Madhyastha. 2024. LLM-Assisted Visual Analytics: Opportunities and Challenges. arXiv preprint arXiv:2409.02691 (2024)."},{"key":"e_1_3_2_1_23_1","volume-title":"Geometric, physical, and visual optics","author":"Keating Michael P","unstructured":"Michael P Keating. 1988. Geometric, physical, and visual optics. Elsevier Health Sciences."},{"key":"e_1_3_2_1_24_1","unstructured":"Smith Lee. 2025. Bridging the AI Adoption Gap: The Disparity Between Rapid Technological Advancements and Corporate Adaptation. (2025)."},{"key":"e_1_3_2_1_25_1","volume-title":"Eagle: Elevating geometric reasoning through llm-empowered visual instruction tuning. arXiv preprint arXiv:2408.11397","author":"Li Zhihao","year":"2024","unstructured":"Zhihao Li, Yao Du, Yang Liu, Yan Zhang, Yufang Liu, Mengdi Zhang, and Xunliang Cai. 2024. Eagle: Elevating geometric reasoning through llm-empowered visual instruction tuning. arXiv preprint arXiv:2408.11397 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3672758.3672824"},{"key":"e_1_3_2_1_27_1","volume-title":"One for all: Towards training one graph model for all classification tasks. arXiv preprint arXiv:2310.00149","author":"Liu Hao","year":"2023","unstructured":"Hao Liu, Jiarui Feng, Lecheng Kong, Ningyue Liang, Dacheng Tao, Yixin Chen, and Muhan Zhang. 2023a. One for all: Towards training one graph model for all classification tasks. arXiv preprint arXiv:2310.00149 (2023)."},{"key":"e_1_3_2_1_28_1","volume-title":"Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023b. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_29_1","volume-title":"The geometrical optics workbook","author":"Loshin David S","unstructured":"David S Loshin. 2015. The geometrical optics workbook. Elsevier Health Sciences."},{"key":"e_1_3_2_1_30_1","first-page":"43447","article-title":"Chameleon: Plug-and-play compositional reasoning with large language models","volume":"36","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. Advances in Neural Information Processing Systems, Vol. 36 (2023), 43447-43478.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","volume-title":"Mono-internvl: Pushing the boundaries of monolithic multimodal large language models with endogenous visual pre-training. arXiv preprint arXiv:2410.08202","author":"Luo Gen","year":"2024","unstructured":"Gen Luo, Xue Yang, Wenhan Dou, Zhaokai Wang, Jifeng Dai, Yu Qiao, and Xizhou Zhu. 2024. Mono-internvl: Pushing the boundaries of monolithic multimodal large language models with endogenous visual pre-training. arXiv preprint arXiv:2410.08202 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"European Conference on Computer Vision. Springer, 417-435","author":"Ma Chuofan","year":"2024","unstructured":"Chuofan Ma, Yi Jiang, Jiannan Wu, Zehuan Yuan, and Xiaojuan Qi. 2024. Groma: Localized visual tokenization for grounding multimodal large language models. In European Conference on Computer Vision. Springer, 417-435."},{"key":"e_1_3_2_1_33_1","first-page":"6","article-title":"Introducing meta llama 3: The most capable openly available llm to date","volume":"2","author":"Meta AI","year":"2024","unstructured":"AI Meta. 2024. Introducing meta llama 3: The most capable openly available llm to date. Meta AI, Vol. 2, 5 (2024), 6.","journal-title":"Meta AI"},{"key":"e_1_3_2_1_34_1","volume-title":"Retrieval augmented generation with multi-modal llm framework for wireless environments. arXiv preprint arXiv:2503.07670","author":"Mohsin Muhammad Ahmed","year":"2025","unstructured":"Muhammad Ahmed Mohsin, Ahsan Bilal, Sagnik Bhattacharya, and John M Cioffi. 2025. Retrieval augmented generation with multi-modal llm framework for wireless environments. arXiv preprint arXiv:2503.07670 (2025)."},{"key":"e_1_3_2_1_35_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_37_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_38_1","first-page":"701","article-title":"State of the art on neural rendering. In Computer Graphics Forum, , Vol. 39","author":"Tewari Ayush","year":"2020","unstructured":"Ayush Tewari, Ohad Fried, Justus Thies, Vincent Sitzmann, Stephen Lombardi, Kalyan Sunkavalli, Ricardo Martin-Brualla, Tomas Simon, Jason Saragih, Matthias Nie\u00dfner, et al., 2020. State of the art on neural rendering. In Computer Graphics Forum, , Vol. 39. Wiley Online Library, 701-727.","journal-title":"Wiley Online Library"},{"key":"e_1_3_2_1_39_1","volume-title":"AI-Driven Robotics for Free-Space Optics. arXiv preprint arXiv:2505.17985","author":"Uddin Shiekh Zia","year":"2025","unstructured":"Shiekh Zia Uddin, Sachin Vaidya, Shrish Choudhary, Zhuo Chen, Raafat K Salib, Luke Huang, Dirk R Englund, and Marin Solja\u010di\u0107. 2025. AI-Driven Robotics for Free-Space Optics. arXiv preprint arXiv:2505.17985 (2025)."},{"key":"e_1_3_2_1_40_1","unstructured":"Peng Wang Shuai Bai Sinan Tan Shijie Wang Zhihao Fan Jinze Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge et al. 2024a. 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_41_1","unstructured":"Xinlong Wang Xiaosong Zhang Zhengxiong Luo Quan Sun Yufeng Cui Jinsheng Wang Fan Zhang Yueze Wang Zhen Li Qiying Yu et al. 2024c. Emu3: Next-token prediction is all you need. arXiv preprint arXiv:2409.18869 (2024)."},{"key":"e_1_3_2_1_42_1","volume-title":"LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods. arXiv preprint arXiv:2407.00322","author":"Wang Zhenhua","year":"2024","unstructured":"Zhenhua Wang, Guang Xu, and Ming Ren. 2024b. LLM-Generated Natural Language Meets Scaling Laws: New Explorations and Data Augmentation Methods. arXiv preprint arXiv:2407.00322 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3607827.3616839"},{"key":"e_1_3_2_1_44_1","volume-title":"The Thirteenth International Conference on Learning Representations.","author":"Zhang Lvmin","year":"2025","unstructured":"Lvmin Zhang, Anyi Rao, and Maneesh Agrawala. 2025a. Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport. In The Thirteenth International Conference on Learning Representations."},{"key":"e_1_3_2_1_45_1","volume-title":"Wei Lin Wang, and Yu Luo","author":"Zhang Long","year":"2025","unstructured":"Long Zhang, Meng Zhang, Wei Lin Wang, and Yu Luo. 2025c. Simulation as Reality? The Effectiveness of LLM-Generated Data in Open-ended Question Assessment. arXiv preprint arXiv:2502.06371 (2025)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Zicheng Zhang Junying Wang Yijin Guo Farong Wen Zijian Chen Hanqing Wang Wenzhe Li Lu Sun Yingjie Zhou Jianbo Zhang Bowen Yan Ziheng Jia Jiahao Xiao Yuan Tian Xiangyang Zhu Kaiwei Zhang Chunyi Li Xiaohong Liu Xiongkuo Min Qi Jia and Guangtao Zhai. 2025b. AIBench: Towards Trustworthy Evaluation Under The 45\u00b0 Law. https:\/\/aiben.ch\/.","DOI":"10.1016\/j.displa.2025.103255"},{"key":"e_1_3_2_1_47_1","volume-title":"Llm-optic: Unveiling the capabilities of large language models for universal visual grounding. arXiv preprint arXiv:2405.17104","author":"Zhao Haoyu","year":"2024","unstructured":"Haoyu Zhao, Wenhang Ge, and Ying-cong Chen. 2024. Llm-optic: Unveiling the capabilities of large language models for universal visual grounding. arXiv preprint arXiv:2405.17104 (2024)."},{"key":"e_1_3_2_1_48_1","volume-title":"Envisioning beyond the pixels: Benchmarking reasoning-informed visual editing. arXiv preprint arXiv:2504.02826","author":"Zhao Xiangyu","year":"2025","unstructured":"Xiangyu Zhao, Peiyuan Zhang, Kexian Tang, Hao Li, Zicheng Zhang, Guangtao Zhai, Junchi Yan, Hua Yang, Xue Yang, and Haodong Duan. 2025. Envisioning beyond the pixels: Benchmarking reasoning-informed visual editing. arXiv preprint arXiv:2504.02826 (2025)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.iheduc.2024.100990"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3758207","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:58:54Z","timestamp":1765310334000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3758207"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":49,"alternative-id":["10.1145\/3746027.3758207","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3758207","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"}}]}}