{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:12Z","timestamp":1786120812787,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["NSFCU23B2055\/NSFC62306276"],"award-info":[{"award-number":["NSFCU23B2055\/NSFC62306276"]}]},{"name":"New Generation Artificial Intelligence-National Science and Technology Major Project 2030","award":["2025ZD0122800"],"award-info":[{"award-number":["2025ZD0122800"]}]},{"name":"Yongjiang Talent Introduction Programme","award":["2022A-238-G"],"award-info":[{"award-number":["2022A-238-G"]}]},{"name":"Fundamental Research Funds for the Central Universities","award":["226-2023-00138"],"award-info":[{"award-number":["226-2023-00138"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817552","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"10114-10125","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniPhys: Knowledge-Graph-Driven Benchmarking and Collective Optimization for Physical Commonsense in Text-to-Image Generation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0887-4445","authenticated-orcid":false,"given":"Yajing","family":"Xu","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2783-7398","authenticated-orcid":false,"given":"Yarong","family":"Lan","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4643-6750","authenticated-orcid":false,"given":"Jiaoyan","family":"Chen","sequence":"additional","affiliation":[{"name":"The University of Manchester, Manchester, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4046-1003","authenticated-orcid":false,"given":"Yichi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9779-2088","authenticated-orcid":false,"given":"Jeff Z.","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5344-1225","authenticated-orcid":false,"given":"Mingchen","family":"Tu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Ningbo, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3511-5139","authenticated-orcid":false,"given":"Zhizhen","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8429-9326","authenticated-orcid":false,"given":"Wen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5496-7442","authenticated-orcid":false,"given":"Huajun","family":"Chen","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V39I2.32168"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.22705"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2025.EMNLP-MAIN.636"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2501.17811"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2509.20427"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2510.26583"},{"key":"e_1_3_2_1_7_1","volume-title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=FPnUhsQJ5B"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2305.16381"},{"key":"e_1_3_2_1_9_1","volume-title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Feng Weixi","year":"2023","unstructured":"Weixi Feng, Xuehai He, Tsu-Jui Fu, Varun Jampani, Arjun R. Akula, Pradyumna Narayana, Sugato Basu, Xin Eric Wang, and William Yang Wang. 2023. Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=PUIqjT4rzq7"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.07546"},{"key":"e_1_3_2_1_11_1","unstructured":"Google DeepMind. 2025. Gemini 3 Pro Image (Nano Banana Pro). https:\/\/ai.google.dev\/gemini-api\/docs\/gemini-3. Accessed: 2026-02-09."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01467"},{"key":"e_1_3_2_1_13_1","volume-title":"Optimizing Prompts for Text-to-Image Generation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023","author":"Hao Yaru","year":"2023","unstructured":"Yaru Hao, Zewen Chi, Li Dong, and Furu Wei. 2023. Optimizing Prompts for Text-to-Image Generation. In Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023, Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/ d346d91999074dd8d6073d4c3b13733b-Abstract-Conference.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/AAAI.V38I3.27986"},{"key":"e_1_3_2_1_15_1","volume-title":"Ronan Le Bras, and Yejin Choi","author":"Hessel Jack","year":"2021","unstructured":"Jack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras, and Yejin Choi. 2021. CLIPScore: A Reference-free Evaluation Metric for Image Captioning. In EMNLP (1). Association for Computational Linguistics, 7514-7528."},{"key":"e_1_3_2_1_16_1","first-page":"6626","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium. In NIPS. 6626-6637.","journal-title":"NIPS."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2506.15742"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2406.11802"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.07265"},{"key":"e_1_3_2_1_21_1","unstructured":"OpenAI. 2024. GPT-4o API Documentation (Snapshot: 2024-11-20). https:\/\/platform.openai.com\/docs\/models\/gpt-4o."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"J.Z. Pan G. Vetere J.M. Gomez-Perez and H. Wu (Eds.). 2017. Exploiting Linked Data and Knowledge Graphs for Large Organisations. Springer.","DOI":"10.1007\/978-3-319-45654-6"},{"key":"e_1_3_2_1_23_1","volume-title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges. Transactions on Graph Data and Knowledge","author":"Pan Jeff Z.","year":"2023","unstructured":"Jeff Z. Pan, Simon Razniewski, Jan-Christoph Kalo, Sneha Singhania, Jiaoyan Chen, Stefan Dietze, Hajira Jabeen, Janna Omeliyanenko, Wen Zhang, Matteo Lissandrini, Russa Biswas, Gerard de Melo, Angela Bonifati, Edlira Vakaj, Mauro Dragoni, and Damien Graux. 2023. Large Language Models and Knowledge Graphs: Opportunities and Challenges. Transactions on Graph Data and Knowledge (2023), 1-38."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/2023.EMNLP-MAIN.494"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.21758"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_27_1","volume-title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L. Denton, Seyed Kamyar Seyed Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022, Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh (Eds.). http:\/\/papers.nips.cc\/paper_files\/paper\/2022\/hash\/ec795aeadae0b7d230fa35cbaf04c041-Abstract-Conference.html"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2507.06261"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2511.22699"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2503.20314"},{"key":"e_1_3_2_1_31_1","unstructured":"Chenfei Wu Jiahao Li Jingren Zhou Junyang Lin Kaiyuan Gao Kun Yan Shengming Yin Shuai Bai Xiao Xu Yilei Chen Yuxiang Chen Zecheng Tang Zekai Zhang Zhengyi Wang An Yang Bowen Yu Chen Cheng Dayiheng Liu Deqing Li Hang Zhang Hao Meng Hu Wei Jingyuan Ni Kai Chen Kuan Cao Liang Peng Lin Qu Minggang Wu Peng Wang Shuting Yu Tingkun Wen Wensen Feng Xiaoxiao Xu Yi Wang Yichang Zhang Yongqiang Zhu Yujia Wu Yuxuan Cai and Zenan Liu. 2025. Qwen-Image Technical Report. CoRR abs\/2508.02324 (2025). arXiv:2508.02324 doi:10.48550\/ARXIV.2508.02324"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0700"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.37"},{"key":"e_1_3_2_1_34_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Yang Chengrun","year":"2024","unstructured":"Chengrun Yang, Xuezhi Wang, Yifeng Lu, Hanxiao Liu, Quoc V. Le, Denny Zhou, and Xinyun Chen. 2024. Large Language Models as Optimizers. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=Bb4VGOWELI"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2505.01490"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:28:17Z","timestamp":1786066097000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817552"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":35,"alternative-id":["10.1145\/3770855.3817552","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817552","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}