{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:41Z","timestamp":1786120841240,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":42,"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":["62471394"],"award-info":[{"award-number":["62471394"]}]},{"name":"National Natural Science Foundation of China","award":["U21B2041"],"award-info":[{"award-number":["U21B2041"]}]},{"name":"National Natural Science Foundation of China","award":["62306241"],"award-info":[{"award-number":["62306241"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817743","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"6865-6874","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Relaxed Bipartite Matching with Structural Inertia for Efficient Diffusion"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3300-0805","authenticated-orcid":false,"given":"Qing","family":"Zhou","sequence":"first","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7438-4874","authenticated-orcid":false,"given":"Xiyao","family":"Gong","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1921-5658","authenticated-orcid":false,"given":"Weiming","family":"Wu","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi Province, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2303-8995","authenticated-orcid":false,"given":"Yuyu","family":"Jia","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, Shaanxi, 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":"10.1109\/CVPR52729.2023.02171"},{"key":"e_1_3_2_1_2_1","volume-title":"International Conference on Learning Representations.","author":"Bolya Daniel","year":"2023","unstructured":"Daniel Bolya, Cheng-Yang Fu, Xiaoliang Dai, Peizhao Zhang, Christoph Feichtenhofer, and Judy Hoffman. 2023. Token Merging: Your ViT but Faster. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_3_1","volume-title":"Token Merging for Fast Stable Diffusion. In CVPR Workshops.","author":"Bolya Daniel","year":"2023","unstructured":"Daniel Bolya and Judy Hoffman. 2023. Token Merging for Fast Stable Diffusion. In CVPR Workshops."},{"key":"e_1_3_2_1_4_1","volume-title":"Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325","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. arXiv preprint arXiv:1504.00325 (2015)."},{"key":"e_1_3_2_1_5_1","volume-title":"CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models. arXiv preprint arXiv:2502.00433","author":"Cheng Xinle","year":"2025","unstructured":"Xinle Cheng, Zhuoming Chen, and Zhihao Jia. 2025. CAT Pruning: Cluster-Aware Token Pruning For Text-to-Image Diffusion Models. arXiv preprint arXiv:2502.00433 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_7_1","volume-title":"V34","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, V34 (2021), 8780-8794."},{"key":"e_1_3_2_1_8_1","volume-title":"Hicache: Training-free acceleration of diffusion models via hermite polynomial-based feature caching. arXiv preprint arXiv:2508.16984","author":"Feng Liang","year":"2025","unstructured":"Liang Feng, Shikang Zheng, Jiacheng Liu, Yuqi Lin, Qinming Zhou, Peiliang Cai, Xinyu Wang, Junjie Chen, Chang Zou, Yue Ma, et al., 2025. Hicache: Training-free acceleration of diffusion models via hermite polynomial-based feature caching. arXiv preprint arXiv:2508.16984 (2025)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"e_1_3_2_1_10_1","volume-title":"V30","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. Advances in neural information processing systems, V30 (2017)."},{"key":"e_1_3_2_1_11_1","volume-title":"V33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, V33 (2020), 6840-6851."},{"key":"e_1_3_2_1_12_1","volume-title":"Accelerating diffusion language model inference via efficient kv caching and guided diffusion. arXiv preprint arXiv:2505.21467","author":"Hu Zhanqiu","year":"2025","unstructured":"Zhanqiu Hu, Jian Meng, Yash Akhauri, Mohamed S Abdelfattah, Jae-sun Seo, Zhiru Zhang, and Udit Gupta. 2025. Accelerating diffusion language model inference via efficient kv caching and guided diffusion. arXiv preprint arXiv:2505.21467 (2025)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746252.3761406"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.11.139"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-025-06265-z"},{"key":"e_1_3_2_1_16_1","volume-title":"DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion. arXiv preprint arXiv:2510.20766","author":"Issachar Noam","year":"2025","unstructured":"Noam Issachar, Guy Yariv, Sagie Benaim, Yossi Adi, Dani Lischinski, and Raanan Fattal. 2025. DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion. arXiv preprint arXiv:2510.20766 (2025)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"e_1_3_2_1_18_1","volume-title":"Language to Multimodality. arXiv preprint arXiv:2505.18227","author":"Kong Zhenglun","year":"2025","unstructured":"Zhenglun Kong, Yize Li, Fanhu Zeng, Lei Xin, Shvat Messica, Xue Lin, Pu Zhao, Manolis Kellis, Hao Tang, and Marinka Zitnik. 2025. Token Reduction Should Go Beyond Efficiency in Generative Models-From Vision, Language to Multimodality. arXiv preprint arXiv:2505.18227 (2025)."},{"key":"e_1_3_2_1_19_1","unstructured":"Black Forest Labs. 2024. FLUX. https:\/\/github.com\/black-forest-labs\/flux."},{"key":"e_1_3_2_1_20_1","volume-title":"ToMA: Token Merge with Attention for Diffusion Models. In Forty-second International Conference on Machine Learning.","author":"Lu Wenbo","year":"2025","unstructured":"Wenbo Lu, Shaoyi Zheng, Yuxuan Xia, and Shengjie Wang. 2025. ToMA: Token Merge with Attention for Diffusion Models. In Forty-second International Conference on Machine Learning."},{"key":"e_1_3_2_1_21_1","volume-title":"A comprehensive survey on knowledge distillation of diffusion models. arXiv preprint arXiv:2304.04262","author":"Luo Weijian","year":"2023","unstructured":"Weijian Luo. 2023. A comprehensive survey on knowledge distillation of diffusion models. arXiv preprint arXiv:2304.04262 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"e_1_3_2_1_23_1","first-page":"3433","article-title":"An effective and efficient algorithm for K-means clustering with new formulation","volume":"35","author":"Nie Feiping","year":"2022","unstructured":"Feiping Nie, Ziheng Li, Rong Wang, and Xuelong Li. 2022. An effective and efficient algorithm for K-means clustering with new formulation. IEEE Transactions on Knowledge and Data Engineering, V35, 4 (2022), 3433-3443.","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_25_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","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, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_26_1","volume-title":"Atiyeh Gh Moghadam, and Ahmad Nickabadi","author":"Saghatchian Omid","year":"2025","unstructured":"Omid Saghatchian, Atiyeh Gh Moghadam, and Ahmad Nickabadi. 2025. Cached Adaptive Token Merging: Dynamic Token Reduction and Redundant Computation Elimination in Diffusion Model. arXiv preprint arXiv:2501.00946 (2025)."},{"key":"e_1_3_2_1_27_1","volume-title":"Burcu Karagol Ayan, Tim Salimans, et al.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al., 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in neural information processing systems, V35 (2022), 36479-36494."},{"key":"e_1_3_2_1_28_1","volume-title":"Todo: Token downsampling for efficient generation of high-resolution images. arXiv preprint arXiv:2402.13573","author":"Smith Ethan","year":"2024","unstructured":"Ethan Smith, Nayan Saxena, and Aninda Saha. 2024. Todo: Token downsampling for efficient generation of high-resolution images. arXiv preprint arXiv:2402.13573 (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Improved techniques for training consistency models. arXiv preprint arXiv:2310.14189","author":"Song Yang","year":"2023","unstructured":"Yang Song and Prafulla Dhariwal. 2023. Improved techniques for training consistency models. arXiv preprint arXiv:2310.14189 (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"Yang Song Prafulla Dhariwal Mark Chen and Ilya Sutskever. 2023. Consistency models. (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456","author":"Song Yang","year":"2020","unstructured":"Yang Song, Jascha Sohl-Dickstein, Diederik P Kingma, Abhishek Kumar, Stefano Ermon, and Ben Poole. 2020. Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)."},{"key":"e_1_3_2_1_32_1","volume-title":"Sdxs: Real-time one-step latent diffusion models with image conditions. arXiv preprint arXiv:2403.16627","author":"Song Yuda","year":"2024","unstructured":"Yuda Song, Zehao Sun, and Xuanwu Yin. 2024. Sdxs: Real-time one-step latent diffusion models with image conditions. arXiv preprint arXiv:2403.16627 (2024)."},{"key":"e_1_3_2_1_33_1","volume-title":"International conference on machine learning. PMLR, 10347-10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347-10357."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01521"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"e_1_3_2_1_36_1","volume-title":"Stochastic runge-kutta methods: Provable acceleration of diffusion models. arXiv preprint arXiv:2410.04760","author":"Wu Yuchen","year":"2024","unstructured":"Yuchen Wu, Yuxin Chen, and Yuting Wei. 2024. Stochastic runge-kutta methods: Provable acceleration of diffusion models. arXiv preprint arXiv:2410.04760 (2024)."},{"key":"e_1_3_2_1_37_1","volume-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, V36","author":"Xu Jiazheng","year":"2023","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2023. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, V36 (2023), 15903-15935."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02333"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33071"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02185"},{"key":"e_1_3_2_1_41_1","volume-title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference. In International Conference on Machine Learning. PMLR, 76397-76413","author":"Zhang Jintao","year":"2025","unstructured":"Jintao Zhang, Chendong Xiang, Haofeng Huang, Jia Wei, Haocheng Xi, Jun Zhu, and Jianfei Chen. 2025d. SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference. In International Conference on Machine Learning. PMLR, 76397-76413."},{"key":"e_1_3_2_1_42_1","volume-title":"Fast Video Generation with Sliding Tile Attention. In International Conference on Machine Learning. PMLR, 74714-74731","author":"Zhang Peiyuan","year":"2025","unstructured":"Peiyuan Zhang, Yongqi Chen, Runlong Su, Hangliang Ding, Ion Stoica, Zhengzhong Liu, and Hao Zhang. 2025a. Fast Video Generation with Sliding Tile Attention. In International Conference on Machine Learning. PMLR, 74714-74731."}],"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":"2026-08-07T01:18:39Z","timestamp":1786065519000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817743"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":42,"alternative-id":["10.1145\/3770855.3817743","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817743","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"}}]}}