{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T22:15:08Z","timestamp":1786572908246,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":46,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,7,20]],"date-time":"2025-07-20T00:00:00Z","timestamp":1752969600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"ARC LIEF Grant","award":["LE240100131"],"award-info":[{"award-number":["LE240100131"]}]},{"name":"ARC Linkage Grant","award":["LP230201022"],"award-info":[{"award-number":["LP230201022"]}]},{"name":"ARC Discovery Grant","award":["DP240102050"],"award-info":[{"award-number":["DP240102050"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,7,20]]},"DOI":"10.1145\/3690624.3709222","type":"proceedings-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T18:48:32Z","timestamp":1743792512000},"page":"1633-1644","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["ProgDiffusion: Progressively Self-encoding Diffusion Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5494-0768","authenticated-orcid":false,"given":"Zhangkai","family":"Wu","sequence":"first","affiliation":[{"name":"Macquarie University, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7558-7200","authenticated-orcid":false,"given":"Xuhui","family":"Fan","sequence":"additional","affiliation":[{"name":"Macquarie University, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1562-9429","authenticated-orcid":false,"given":"Longbing","family":"Cao","sequence":"additional","affiliation":[{"name":"Macquarie University, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,7,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Label-efficient Semantic Segmentation with Diffusion Models. ICLR","author":"Baranchuk Dmitry","year":"2022","unstructured":"Dmitry Baranchuk, Ivan Rubachev, Andrey Voynov, Valentin Khrulkov, and Artem Babenko. 2022. Label-efficient Semantic Segmentation with Diffusion Models. ICLR (2022)."},{"key":"e_1_3_2_2_2_1","volume-title":"Large scale GAN training for High Fidelity Natural Image Synthesis. arXiv preprint arXiv:1809.11096","author":"Brock Andrew","year":"2018","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large scale GAN training for High Fidelity Natural Image Synthesis. arXiv preprint arXiv:1809.11096 (2018)."},{"key":"e_1_3_2_2_3_1","volume-title":"Understanding Disentangling in beta-VAE. NeurIPS","author":"Burgess Christopher P","year":"2017","unstructured":"Christopher P Burgess, Irina Higgins, Arka Pal, Loic Matthey, Nick Watters, Guillaume Desjardins, and Alexander Lerchner. 2017. Understanding Disentangling in beta-VAE. NeurIPS (2017)."},{"key":"e_1_3_2_2_4_1","volume-title":"Deconstructing Denoising Diffusion Models for Self-supervised Learning. arXiv preprint arXiv:2401.14404","author":"Chen Xinlei","year":"2024","unstructured":"Xinlei Chen, Zhuang Liu, Saining Xie, and Kaiming He. 2024. Deconstructing Denoising Diffusion Models for Self-supervised Learning. arXiv preprint arXiv:2401.14404 (2024)."},{"key":"e_1_3_2_2_5_1","volume-title":"Diffusion Models beat GANs on Image Synthesis. NeurIPS","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion Models beat GANs on Image Synthesis. NeurIPS (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Generative Adversarial Nets. NeurIPS","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. NeurIPS (2014)."},{"key":"e_1_3_2_2_7_1","volume-title":"Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models. CVPR","author":"Guo Jiayi","year":"2024","unstructured":"Jiayi Guo, Xingqian Xu, Yifan Pu, Zanlin Ni, Chaofei Wang, Manushree Vasu, Shiji Song, Gao Huang, and Humphrey Shi. 2024. Smooth Diffusion: Crafting Smooth Latent Spaces in Diffusion Models. CVPR (2024)."},{"key":"e_1_3_2_2_8_1","volume-title":"Unsupervised Semantic Correspondence using Stable Diffusion. NeurIPS","author":"Hedlin Eric","year":"2024","unstructured":"Eric Hedlin, Gopal Sharma, Shweta Mahajan, Hossam Isack, Abhishek Kar, Andrea Tagliasacchi, and Kwang Moo Yi. 2024. Unsupervised Semantic Correspondence using Stable Diffusion. NeurIPS (2024)."},{"key":"e_1_3_2_2_9_1","volume-title":"Prompt-to-prompt Image Editing with Cross Attention Control. ICLR","author":"Hertz Amir","year":"2023","unstructured":"Amir Hertz, Ron Mokady, Jay Tenenbaum, Kfir Aberman, Yael Pritch, and Daniel Cohen-Or. 2023. Prompt-to-prompt Image Editing with Cross Attention Control. ICLR (2023)."},{"key":"e_1_3_2_2_10_1","volume-title":"beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. ICLR","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher P Burgess, Xavier Glorot, Matthew M Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework. ICLR (2017)."},{"key":"e_1_3_2_2_11_1","volume-title":"Denoising Diffusion Probabilistic Models. NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. NeurIPS (2020)."},{"key":"e_1_3_2_2_12_1","volume-title":"Classifier-free Diffusion Guidance. NeurIPS","author":"Ho Jonathan","year":"2021","unstructured":"Jonathan Ho and Tim Salimans. 2021. Classifier-free Diffusion Guidance. NeurIPS (2021)."},{"key":"e_1_3_2_2_13_1","volume-title":"Soda: Bottleneck Diffusion Models for Representation Learning. CVPR","author":"Hudson Drew A","year":"2024","unstructured":"Drew A Hudson, Daniel Zoran, Mateusz Malinowski, Andrew K Lampinen, Andrew Jaegle, James L McClelland, Loic Matthey, Felix Hill, and Alexander Lerchner. 2024. Soda: Bottleneck Diffusion Models for Representation Learning. CVPR (2024)."},{"key":"e_1_3_2_2_14_1","volume-title":"Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma and Max Welling. 2013. Auto-encoding Variational Bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_2_15_1","volume-title":"Sd4match: Learning to prompt Stable Diffusion Model for Semantic Matching. CVPR","author":"Li Xinghui","year":"2024","unstructured":"Xinghui Li, Jingyi Lu, Kai Han, and Victor Adrian Prisacariu. 2024. Sd4match: Learning to prompt Stable Diffusion Model for Semantic Matching. CVPR (2024)."},{"key":"e_1_3_2_2_16_1","volume-title":"Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation. WACV","author":"Lu Zeyu","year":"2024","unstructured":"Zeyu Lu, Chengyue Wu, Xinyuan Chen, Yaohui Wang, Lei Bai, Yu Qiao, and Xihui Liu. 2024. Hierarchical Diffusion Autoencoders and Disentangled Image Manipulation. WACV (2024)."},{"key":"e_1_3_2_2_17_1","volume-title":"Aleksander Holynski, and Trevor Darrell.","author":"Luo Grace","year":"2024","unstructured":"Grace Luo, Lisa Dunlap, Dong Huk Park, Aleksander Holynski, and Trevor Darrell. 2024. Diffusion hyperfeatures: Searching through Time and Space for Semantic Correspondence. NeurIPS (2024)."},{"key":"e_1_3_2_2_18_1","unstructured":"Alireza Makhzani Jonathon Shlens Navdeep Jaitly Ian Goodfellow and Brendan Frey. 2016. Adversarial Autoencoders. ICLR (2016)."},{"key":"e_1_3_2_2_19_1","volume-title":"Do text-free Diffusion Models Learn Discriminative Visual Representations? arXiv preprint arXiv:2311.17921","author":"Mukhopadhyay Soumik","year":"2023","unstructured":"Soumik Mukhopadhyay, Matthew Gwilliam, Yosuke Yamaguchi, Vatsal Agarwal, Namitha Padmanabhan, Archana Swaminathan, Tianyi Zhou, and Abhinav Shrivastava. 2023. Do text-free Diffusion Models Learn Discriminative Visual Representations? arXiv preprint arXiv:2311.17921 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Improved Denoising Diffusion Probabilistic Models. ICML","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. ICML (2021)."},{"key":"e_1_3_2_2_21_1","volume-title":"Masked Diffusion as Self-Supervised Representation Learner. arXiv preprint arXiv:2308.05695","author":"Pan Zixuan","year":"2023","unstructured":"Zixuan Pan, Jianxu Chen, and Yiyu Shi. 2023. Masked Diffusion as Self-Supervised Representation Learner. arXiv preprint arXiv:2308.05695 (2023)."},{"key":"e_1_3_2_2_22_1","volume-title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation. CVPR","author":"Parmar Gaurav","year":"2022","unstructured":"Gaurav Parmar, Richard Zhang, and Jun-Yan Zhu. 2022. On Aliased Resizing and Surprising Subtleties in GAN Evaluation. CVPR (2022)."},{"key":"e_1_3_2_2_23_1","volume-title":"Vincent Dumoulin, and Aaron Courville.","author":"Perez Ethan","year":"2018","unstructured":"Ethan Perez, Florian Strub, Harm De Vries, Vincent Dumoulin, and Aaron Courville. 2018. Film: Visual Reasoning with a General Conditioning Layer. AAAI (2018)."},{"key":"e_1_3_2_2_24_1","volume-title":"Diffusion Autoencoders: Toward a Meaningful and Decodable Representation. CVPR","author":"Preechakul Konpat","year":"2022","unstructured":"Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa, and Supasorn Suwajanakorn. 2022. Diffusion Autoencoders: Toward a Meaningful and Decodable Representation. CVPR (2022)."},{"key":"e_1_3_2_2_25_1","volume-title":"High-resolution Image Synthesis with Latent Diffusion Models. CVPR","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-resolution Image Synthesis with Latent Diffusion Models. CVPR (2022)."},{"key":"e_1_3_2_2_26_1","volume-title":"Controlvae: Controllable Variational Autoencoder. ICML","author":"Shao Huajie","year":"2020","unstructured":"Huajie Shao, Shuochao Yao, Dachun Sun, Aston Zhang, Shengzhong Liu, Dongxin Liu, Jun Wang, and Tarek Abdelzaher. 2020. Controlvae: Controllable Variational Autoencoder. ICML (2020)."},{"key":"e_1_3_2_2_27_1","volume-title":"Animating Rotation with Quaternion Curves. Conference on Computer Graphics and Interactive Techniques","author":"Shoemake Ken","year":"1985","unstructured":"Ken Shoemake. 1985. Animating Rotation with Quaternion Curves. Conference on Computer Graphics and Interactive Techniques (1985)."},{"key":"e_1_3_2_2_28_1","volume-title":"Denoising Diffusion Implicit Models. arXiv preprint arXiv:2010.02502","author":"Song Jiaming","year":"2020","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2020. Denoising Diffusion Implicit Models. arXiv preprint arXiv:2010.02502 (2020)."},{"key":"e_1_3_2_2_29_1","volume-title":"Cheng Perng Phoo, and Bharath Hariharan","author":"Tang Luming","year":"2023","unstructured":"Luming Tang, Menglin Jia, Qianqian Wang, Cheng Perng Phoo, and Bharath Hariharan. 2023. Emergent Correspondence from Image Diffusion. NeurIPS (2023)."},{"key":"e_1_3_2_2_30_1","volume-title":"Plug-and-play Diffusion Features for Text-driven Image-to-image Translation. CVPR","author":"Tumanyan Narek","year":"2023","unstructured":"Narek Tumanyan, Michal Geyer, Shai Bagon, and Tali Dekel. 2023. Plug-and-play Diffusion Features for Text-driven Image-to-image Translation. CVPR (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"Christopher De Sa, and Volodymyr Kuleshov","author":"Wang Yingheng","year":"2023","unstructured":"Yingheng Wang, Yair Schiff, Aaron Gokaslan, Weishen Pan, Fei Wang, Christopher De Sa, and Volodymyr Kuleshov. 2023. InfoDiffusion: Representation Learning Using Information Maximizing Diffusion Models. NeurIPS (2023)."},{"key":"e_1_3_2_2_32_1","volume-title":"Diffusion Models as Masked Autoencoders. ICCV","author":"Wei Chen","year":"2023","unstructured":"Chen Wei, Karttikeya Mangalam, Po-Yao Huang, Yanghao Li, Haoqi Fan, Hu Xu, Huiyu Wang, Cihang Xie, Alan Yuille, and Christoph Feichtenhofer. 2023. Diffusion Models as Masked Autoencoders. ICCV (2023)."},{"key":"e_1_3_2_2_33_1","unstructured":"Yuxin Wu and Kaiming He. 2018. Group Normalization. ECCV (2018)."},{"key":"e_1_3_2_2_34_1","volume-title":"C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior. arXiv preprint arXiv:2309.13303","author":"Wu Zhangkai","year":"2023","unstructured":"Zhangkai Wu and Longbing Cao. 2023. C2VAE: Gaussian Copula-based VAE Differing Disentangled from Coupled Representations with Contrastive Posterior. arXiv preprint arXiv:2309.13303 (2023)."},{"key":"e_1_3_2_2_35_1","volume-title":"eVAE: Evolutionary Variational Autoencoder. TNNLS","author":"Wu Zhangkai","year":"2024","unstructured":"Zhangkai Wu, Longbing Cao, and Lei Qi. 2024a. eVAE: Evolutionary Variational Autoencoder. TNNLS (2024)."},{"key":"e_1_3_2_2_36_1","volume-title":"Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection. arXiv preprint arXiv:2401.03341","author":"Wu Zhangkai","year":"2024","unstructured":"Zhangkai Wu, Longbing Cao, Qi Zhang, Junxian Zhou, and Hui Chen. 2024b. Weakly Augmented Variational Autoencoder in Time Series Anomaly Detection. arXiv preprint arXiv:2401.03341 (2024)."},{"key":"e_1_3_2_2_37_1","volume-title":"Paramrel: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks. arXiv preprint arXiv:2405.15268","author":"Wu Zhangkai","year":"2024","unstructured":"Zhangkai Wu, Xuhui Fan, Jin Li, Zhilin Zhao, Hui Chen, and Longbing Cao. 2024c. Paramrel: Learning Parameter Space Representation via Progressively Encoding Bayesian Flow Networks. arXiv preprint arXiv:2405.15268 (2024)."},{"key":"e_1_3_2_2_38_1","volume-title":"Denoising Diffusion Autoencoders are Unified Self-supervised Learners. ICCV","author":"Xiang Weilai","year":"2023","unstructured":"Weilai Xiang, Hongyu Yang, Di Huang, and Yunhong Wang. 2023. Denoising Diffusion Autoencoders are Unified Self-supervised Learners. ICCV (2023)."},{"key":"e_1_3_2_2_39_1","volume-title":"Open-vocabulary Panoptic Segmentation with Text-to-image Diffusion Models. CVPR","author":"Xu Jiarui","year":"2023","unstructured":"Jiarui Xu, Sifei Liu, Arash Vahdat, Wonmin Byeon, Xiaolong Wang, and Shalini De Mello. 2023. Open-vocabulary Panoptic Segmentation with Text-to-image Diffusion Models. CVPR (2023)."},{"key":"e_1_3_2_2_40_1","volume-title":"DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models. NeurIPS","author":"Yang Tao","year":"2023","unstructured":"Tao Yang, Yuwang Wang, Yan Lu, and Nanning Zheng. 2023. DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models. NeurIPS (2023)."},{"key":"e_1_3_2_2_41_1","volume-title":"Nashae: Disentangling representations through adversarial covariance minimization. ECCV","author":"Yeats Eric","year":"2022","unstructured":"Eric Yeats, Frank Liu, David Womble, and Hai Li. 2022. Nashae: Disentangling representations through adversarial covariance minimization. ECCV (2022)."},{"key":"e_1_3_2_2_42_1","volume-title":"Eric I-Chao Chang, and Hanwang Zhang","author":"Yue Zhongqi","year":"2024","unstructured":"Zhongqi Yue, Jiankun Wang, Qianru Sun, Lei Ji, Eric I-Chao Chang, and Hanwang Zhang. 2024. Exploring Diffusion Time-steps for Unsupervised Representation Learning. In ICLR."},{"key":"e_1_3_2_2_43_1","volume-title":"Varun Jampani, Deqing Sun, and Ming-Hsuan Yang.","author":"Zhang Junyi","year":"2024","unstructured":"Junyi Zhang, Charles Herrmann, Junhwa Hur, Luisa Polania Cabrera, Varun Jampani, Deqing Sun, and Ming-Hsuan Yang. 2024. A tale of two features: Stable Diffusion Complements Dino for Zero-shot Semantic Correspondence. NeurIPS (2024)."},{"key":"e_1_3_2_2_44_1","volume-title":"Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models. NeurIPS","author":"Zhang Zijian","year":"2022","unstructured":"Zijian Zhang, Zhou Zhao, and Zhijie Lin. 2022. Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models. NeurIPS (2022)."},{"key":"e_1_3_2_2_45_1","volume-title":"InfoVAE: Balancing Learning and Inference in Variational Autoencoders. AAAI","author":"Zhao Shengjia","year":"2019","unstructured":"Shengjia Zhao, Jiaming Song, and Stefano Ermon. 2019. InfoVAE: Balancing Learning and Inference in Variational Autoencoders. AAAI (2019)."},{"key":"e_1_3_2_2_46_1","volume-title":"Unleashing text-to-image Diffusion Models for Visual Perception. ICCV","author":"Zhao Wenliang","year":"2023","unstructured":"Wenliang Zhao, Yongming Rao, Zuyan Liu, Benlin Liu, Jie Zhou, and Jiwen Lu. 2023. Unleashing text-to-image Diffusion Models for Visual Perception. ICCV (2023)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","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 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709222","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3690624.3709222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,16]],"date-time":"2025-08-16T15:45:48Z","timestamp":1755359148000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3690624.3709222"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,20]]},"references-count":46,"alternative-id":["10.1145\/3690624.3709222","10.1145\/3690624"],"URL":"https:\/\/doi.org\/10.1145\/3690624.3709222","relation":{},"subject":[],"published":{"date-parts":[[2025,7,20]]},"assertion":[{"value":"2025-07-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}