{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:27:06Z","timestamp":1765308426886,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":66,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276255"],"award-info":[{"award-number":["62276255"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Postdoctoral Fellowship Program of CPSF","award":["GZC20251175"],"award-info":[{"award-number":["GZC20251175"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2022ZD0119402"],"award-info":[{"award-number":["2022ZD0119402"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755472","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"8399-8408","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["DilateQuant: Accurate and Efficient Quantization-Aware Training for Diffusion Models via Weight Dilation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6852-6784","authenticated-orcid":false,"given":"Xuewen","family":"Liu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6483-1597","authenticated-orcid":false,"given":"Zhikai","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6633-0681","authenticated-orcid":false,"given":"Minghao","family":"Jiang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China and School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5445-3644","authenticated-orcid":false,"given":"Mengjuan","family":"Chen","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7497-712X","authenticated-orcid":false,"given":"Jianquan","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8332-5350","authenticated-orcid":false,"given":"Qingyi","family":"Gu","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, 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":"Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125","author":"Chen Pengtao","year":"2024","unstructured":"Pengtao Chen, Mingzhu Shen, Peng Ye, Jianjian Cao, Chongjun Tu, Christos-Savvas Bouganis, Yiren Zhao, and Tao Chen. 2024. Delta-DiT: A Training-Free Acceleration Method Tailored for Diffusion Transformers. arXiv preprint arXiv:2406.01125 (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_3_1","volume-title":"Cbq: Cross-block quantization for large language models. arXiv preprint arXiv:2312.07950","author":"Ding Xin","year":"2023","unstructured":"Xin Ding, Xiaoyu Liu, Zhijun Tu, Yun Zhang, Wei Li, Jie Hu, Hanting Chen, Yehui Tang, Zhiwei Xiong, Baoqun Yin, et al., 2023. Cbq: Cross-block quantization for large language models. arXiv preprint arXiv:2312.07950 (2023)."},{"key":"e_1_3_2_1_4_1","volume-title":"Learned step size quantization. arXiv preprint arXiv:1902.08153","author":"Esser Steven K","year":"2019","unstructured":"Steven K Esser, Jeffrey L McKinstry, Deepika Bablani, Rathinakumar Appuswamy, and Dharmendra S Modha. 2019. Learned step size quantization. arXiv preprint arXiv:1902.08153 (2019)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00495"},{"key":"e_1_3_2_1_6_1","volume-title":"Efficientdm: Efficient quantization-aware fine-tuning of low-bit diffusion models. arXiv preprint arXiv:2310.03270","author":"He Yefei","year":"2023","unstructured":"Yefei He, Jing Liu, Weijia Wu, Hong Zhou, and Bohan Zhuang. 2023b. Efficientdm: Efficient quantization-aware fine-tuning of low-bit diffusion models. arXiv preprint arXiv:2310.03270 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"PTQD: Accurate Post-Training Quantization for Diffusion Models. arXiv preprint arXiv:2305.10657","author":"He Yefei","year":"2023","unstructured":"Yefei He, Luping Liu, Jing Liu, Weijia Wu, Hong Zhou, and Bohan Zhuang. 2023a. PTQD: Accurate Post-Training Quantization for Diffusion Models. arXiv preprint arXiv:2305.10657 (2023)."},{"key":"e_1_3_2_1_8_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. arXiv preprint arXiv:2104.08718 (2021)."},{"key":"e_1_3_2_1_9_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_10_1","unstructured":"Jonathan Ho William Chan Chitwan Saharia Jay Whang Ruiqi Gao Alexey Gritsenko Diederik P Kingma Ben Poole Mohammad Norouzi David J Fleet et al. 2022. Imagen video: High definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)."},{"key":"e_1_3_2_1_11_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_1_12_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Hoedt Pieter-Jan","year":"2024","unstructured":"Pieter-Jan Hoedt and G\u00fcnter Klambauer. 2024. Principled weight initialisation for input-convex neural networks. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models. arXiv preprint arXiv:2412.16700","author":"Huang Haocheng","year":"2024","unstructured":"Haocheng Huang, Jiaxin Chen, Jinyang Guo, Ruiyi Zhan, and Yunhong Wang. 2024a. TCAQ-DM: Timestep-Channel Adaptive Quantization for Diffusion Models. arXiv preprint arXiv:2412.16700 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00703"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747552"},{"key":"e_1_3_2_1_17_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_18_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.01.029"},{"key":"e_1_3_2_1_20_1","volume-title":"Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models. arXiv preprint arXiv:2411.05007","author":"Li Muyang","year":"2024","unstructured":"Muyang Li, Yujun Lin, Zhekai Zhang, Tianle Cai, Xiuyu Li, Junxian Guo, Enze Xie, Chenlin Meng, Jun-Yan Zhu, and Song Han. 2024a. Svdqunat: Absorbing outliers by low-rank components for 4-bit diffusion models. arXiv preprint arXiv:2411.05007 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"e_1_3_2_1_22_1","volume-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426","author":"Li Yuhang","year":"2021","unstructured":"Yuhang Li, Ruihao Gong, Xu Tan, Yang Yang, Peng Hu, Qi Zhang, Fengwei Yu, Wei Wang, and Shi Gu. 2021. Brecq: Pushing the limit of post-training quantization by block reconstruction. arXiv preprint arXiv:2102.05426 (2021)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00853"},{"key":"e_1_3_2_1_25_1","volume-title":"Repquant: Towards accurate post-training quantization of large transformer models via scale reparameterization. arXiv preprint arXiv:2402.05628","author":"Li Zhikai","year":"2024","unstructured":"Zhikai Li, Xuewen Liu, Jing Zhang, and Qingyi Gu. 2024b. Repquant: Towards accurate post-training quantization of large transformer models via scale reparameterization. arXiv preprint arXiv:2402.05628 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"e_1_3_2_1_27_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 87-100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_28_1","first-page":"740","volume-title":"Zurich","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part V 13. Springer, 740-755."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02167"},{"key":"e_1_3_2_1_30_1","volume-title":"Enhanced distribution alignment for post-training quantization of diffusion models. arXiv preprint arXiv:2401.04585","author":"Liu Xuewen","year":"2024","unstructured":"Xuewen Liu, Zhikai Li, Junrui Xiao, and Qingyi Gu. 2024. Enhanced distribution alignment for post-training quantization of diffusion models. arXiv preprint arXiv:2401.04585 (2024)."},{"key":"e_1_3_2_1_31_1","volume-title":"Relaxed quantization for discretized neural networks. arXiv preprint arXiv:1810.01875","author":"Louizos Christos","year":"2018","unstructured":"Christos Louizos, Matthias Reisser, Tijmen Blankevoort, Efstratios Gavves, and Max Welling. 2018. Relaxed quantization for discretized neural networks. arXiv preprint arXiv:1810.01875 (2018)."},{"key":"e_1_3_2_1_32_1","volume-title":"Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095","author":"Lu Cheng","year":"2022","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2022. Dpm-solver: Fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"e_1_3_2_1_34_1","volume-title":"International Conference on Machine Learning. PMLR, 7197-7206","author":"Nagel Markus","year":"2020","unstructured":"Markus Nagel, Rana Ali Amjad, Mart Van Baalen, Christos Louizos, and Tijmen Blankevoort. 2020. Up or down? adaptive rounding for post-training quantization. In International Conference on Machine Learning. PMLR, 7197-7206."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00141"},{"key":"e_1_3_2_1_36_1","volume-title":"International Conference on Machine Learning. PMLR, 8162-8171","author":"Nichol Alexander Quinn","year":"2021","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International Conference on Machine Learning. PMLR, 8162-8171."},{"key":"e_1_3_2_1_37_1","volume-title":"International Conference on Artificial Intelligence and Statistics. PMLR, 4474-4484","author":"Niu Chenhao","year":"2020","unstructured":"Chenhao Niu, Yang Song, Jiaming Song, Shengjia Zhao, Aditya Grover, and Stefano Ermon. 2020. Permutation invariant graph generation via score-based generative modeling. In International Conference on Artificial Intelligence and Statistics. PMLR, 4474-4484."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_40_1","first-page":"234","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, 234-241."},{"key":"e_1_3_2_1_41_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, Vol. 35 (2022), 36479-36494."},{"key":"e_1_3_2_1_42_1","volume-title":"Improved techniques for training gans. Advances in neural information processing systems","author":"Salimans Tim","year":"2016","unstructured":"Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. 2016. Improved techniques for training gans. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"e_1_3_2_1_44_1","volume-title":"Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137","author":"Shao Wenqi","year":"2023","unstructured":"Wenqi Shao, Mengzhao Chen, Zhaoyang Zhang, Peng Xu, Lirui Zhao, Zhiqian Li, Kaipeng Zhang, Peng Gao, Yu Qiao, and Ping Luo. 2023. Omniquant: Omnidirectionally calibrated quantization for large language models. arXiv preprint arXiv:2308.13137 (2023)."},{"key":"e_1_3_2_1_45_1","first-page":"17737","article-title":"Post-training sparsity-aware quantization","volume":"34","author":"Shomron Gil","year":"2021","unstructured":"Gil Shomron, Freddy Gabbay, Samer Kurzum, and Uri Weiser. 2021. Post-training sparsity-aware quantization. Advances in Neural Information Processing Systems, Vol. 34 (2021), 17737-17748.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_1","volume-title":"Temporal Dynamic Quantization for Diffusion Models. arXiv preprint arXiv:2306.02316","author":"So Junhyuk","year":"2023","unstructured":"Junhyuk So, Jungwon Lee, Daehyun Ahn, Hyungjun Kim, and Eunhyeok Park. 2023. Temporal Dynamic Quantization for Diffusion Models. arXiv preprint arXiv:2306.02316 (2023)."},{"key":"e_1_3_2_1_47_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_1_48_1","volume-title":"Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems","author":"Song Yang","year":"2019","unstructured":"Yang Song and Stefano Ermon. 2019. Generative modeling by estimating gradients of the data distribution. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_49_1","volume-title":"1.99 bits weight quantization of diffusion model. arXiv preprint arXiv:2406.04333","author":"Sui Yang","year":"2024","unstructured":"Yang Sui, Yanyu Li, Anil Kag, Yerlan Idelbayev, Junli Cao, Ju Hu, Dhritiman Sagar, Bo Yuan, Sergey Tulyakov, and Jian Ren. 2024. Bitsfusion: 1.99 bits weight quantization of diffusion model. arXiv preprint arXiv:2406.04333 (2024)."},{"key":"e_1_3_2_1_50_1","volume-title":"Quest: Low-bit diffusion model quantization via efficient selective finetuning. arXiv preprint arXiv:2402.03666","author":"Wang Haoxuan","year":"2024","unstructured":"Haoxuan Wang, Yuzhang Shang, Zhihang Yuan, Junyi Wu, and Yan Yan. 2024b. Quest: Low-bit diffusion model quantization via efficient selective finetuning. arXiv preprint arXiv:2402.03666 (2024)."},{"key":"e_1_3_2_1_51_1","volume-title":"Lavie: High-quality video generation with cascaded latent diffusion models. International Journal of Computer Vision","author":"Wang Yaohui","year":"2024","unstructured":"Yaohui Wang, Xinyuan Chen, Xin Ma, Shangchen Zhou, Ziqi Huang, Yi Wang, Ceyuan Yang, Yinan He, Jiashuo Yu, Peiqing Yang, et al., 2024a. Lavie: High-quality video generation with cascaded latent diffusion models. International Journal of Computer Vision (2024), 1-20."},{"key":"e_1_3_2_1_52_1","volume-title":"LaVin-DiT: Large Vision Diffusion Transformer. arXiv preprint arXiv:2411.11505","author":"Wang Zhaoqing","year":"2024","unstructured":"Zhaoqing Wang, Xiaobo Xia, Runnan Chen, Dongdong Yu, Changhu Wang, Mingming Gong, and Tongliang Liu. 2024c. LaVin-DiT: Large Vision Diffusion Transformer. arXiv preprint arXiv:2411.11505 (2024)."},{"key":"e_1_3_2_1_53_1","volume-title":"Learning fast samplers for diffusion models by differentiating through sample quality. arXiv preprint arXiv:2202.05830","author":"Watson Daniel","year":"2022","unstructured":"Daniel Watson, William Chan, Jonathan Ho, and Mohammad Norouzi. 2022. Learning fast samplers for diffusion models by differentiating through sample quality. arXiv preprint arXiv:2202.05830 (2022)."},{"key":"e_1_3_2_1_54_1","volume-title":"Outlier suppression: Accurate quantization of large language models by equivalent and optimal shifting and scaling. arXiv preprint arXiv:2304.09145","author":"Wei Xiuying","year":"2023","unstructured":"Xiuying Wei, Yunchen Zhang, Yuhang Li, Xiangguo Zhang, Ruihao Gong, Jinyang Guo, and Xianglong Liu. 2023. Outlier suppression: Accurate quantization of large language models by equivalent and optimal shifting and scaling. arXiv preprint arXiv:2304.09145 (2023)."},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-022-00795-y"},{"key":"e_1_3_2_1_57_1","volume-title":"PTQ4DiT: Post-training Quantization for Diffusion Transformers. arXiv preprint arXiv:2405.16005","author":"Wu Junyi","year":"2024","unstructured":"Junyi Wu, Haoxuan Wang, Yuzhang Shang, Mubarak Shah, and Yan Yan. 2024. PTQ4DiT: Post-training Quantization for Diffusion Transformers. arXiv preprint arXiv:2405.16005 (2024)."},{"key":"e_1_3_2_1_58_1","volume-title":"International Conference on Machine Learning. PMLR, 38087-38099","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Ji Lin, Mickael Seznec, Hao Wu, Julien Demouth, and Song Han. 2023c. Smoothquant: Accurate and efficient post-training quantization for large language models. In International Conference on Machine Learning. PMLR, 38087-38099."},{"key":"e_1_3_2_1_59_1","volume-title":"DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection. IET Image Processing","author":"Xiao Junrui","year":"2023","unstructured":"Junrui Xiao, He Jiang, Zhikai Li, and Qingyi Gu. 2023a. DCIFPN: Deformable cross-scale interaction feature pyramid network for object detection. IET Image Processing (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Patch-wise Mixed-Precision Quantization of Vision Transformer. arXiv preprint arXiv:2305.06559","author":"Xiao Junrui","year":"2023","unstructured":"Junrui Xiao, Zhikai Li, Lianwei Yang, and Qingyi Gu. 2023b. Patch-wise Mixed-Precision Quantization of Vision Transformer. arXiv preprint arXiv:2305.06559 (2023)."},{"key":"e_1_3_2_1_61_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Xu Jiazheng","year":"2024","unstructured":"Jiazheng Xu, Xiao Liu, Yuchen Wu, Yuxuan Tong, Qinkai Li, Ming Ding, Jie Tang, and Yuxiao Dong. 2024. Imagereward: Learning and evaluating human preferences for text-to-image generation. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_62_1","volume-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)."},{"key":"e_1_3_2_1_63_1","volume-title":"Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM. arXiv preprint arXiv:2310.04836","author":"Zhang Luoming","year":"2023","unstructured":"Luoming Zhang, Wen Fei, Weijia Wu, Yefei He, Zhenyu Lou, and Hong Zhou. 2023a. Dual Grained Quantization: Efficient Fine-Grained Quantization for LLM. arXiv preprint arXiv:2310.04836 (2023)."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_65_1","volume-title":"gDDIM: Generalized denoising diffusion implicit models. arXiv preprint arXiv:2206.05564","author":"Zhang Qinsheng","year":"2022","unstructured":"Qinsheng Zhang, Molei Tao, and Yongxin Chen. 2022. gDDIM: Generalized denoising diffusion implicit models. arXiv preprint arXiv:2206.05564 (2022)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00978"}],"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\/3746027.3755472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:23:58Z","timestamp":1765308238000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755472"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":66,"alternative-id":["10.1145\/3746027.3755472","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755472","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"}}]}}