{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:28:38Z","timestamp":1765499318772,"version":"3.48.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761497","type":"proceedings-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T23:59:18Z","timestamp":1762559958000},"page":"5963-5970","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Expert-Guided Diffusion Planner for Auto-Bidding"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8943-7725","authenticated-orcid":false,"given":"Yunshan","family":"Peng","sequence":"first","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7469-1083","authenticated-orcid":false,"given":"Wenzheng","family":"Shu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8045-9061","authenticated-orcid":false,"given":"Jiahao","family":"Sun","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3749-4019","authenticated-orcid":false,"given":"Yanxiang","family":"Zeng","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6566-9171","authenticated-orcid":false,"given":"Jinan","family":"Pang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0149-6867","authenticated-orcid":false,"given":"Wentao","family":"Bai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0545-8041","authenticated-orcid":false,"given":"Yunke","family":"Bai","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7253-0674","authenticated-orcid":false,"given":"Xialong","family":"Liu","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9266-0780","authenticated-orcid":false,"given":"Peng","family":"Jiang","sequence":"additional","affiliation":[{"name":"Kuaishou Technology, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-18714-3_2"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3699824.3699838"},{"key":"e_1_3_2_1_3_1","volume-title":"Learning to poke by poking: Experiential learning of intuitive physics. Advances in neural information processing systems 29","author":"Agrawal Pulkit","year":"2016","unstructured":"Pulkit Agrawal, Ashvin V Nair, Pieter Abbeel, Jitendra Malik, and Sergey Levine. 2016. Learning to poke by poking: Experiential learning of intuitive physics. Advances in neural information processing systems 29 (2016)."},{"key":"e_1_3_2_1_4_1","volume-title":"Is conditional generative modeling all you need for decision making? arXiv preprint arXiv:2211.15657","author":"Ajay Anurag","year":"2022","unstructured":"Anurag Ajay, Yilun Du, Abhi Gupta, Joshua Tenenbaum, Tommi Jaakkola, and Pulkit Agrawal. 2022. Is conditional generative modeling all you need for decision making? arXiv preprint arXiv:2211.15657 (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Scheduled sampling for sequence prediction with recurrent neural networks. Advances in neural information processing systems 28","author":"Bengio Samy","year":"2015","unstructured":"Samy Bengio, Oriol Vinyals, Navdeep Jaitly, and Noam Shazeer. 2015. Scheduled sampling for sequence prediction with recurrent neural networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018702"},{"key":"e_1_3_2_1_7_1","volume-title":"Offline reinforcement learning via high-fidelity generative behavior modeling. arXiv preprint arXiv:2209.14548","author":"Chen Huayu","year":"2022","unstructured":"Huayu Chen, Cheng Lu, Chengyang Ying, Hang Su, and Jun Zhu. 2022. Offline reinforcement learning via high-fidelity generative behavior modeling. arXiv preprint arXiv:2209.14548 (2022)."},{"key":"e_1_3_2_1_8_1","volume-title":"Decision Transformer: Reinforcement Learning via Sequence Modeling. In NeurIPS.","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision Transformer: Reinforcement Learning via Sequence Modeling. In NeurIPS."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1257\/jep.23.3.37"},{"key":"e_1_3_2_1_10_1","volume-title":"Unveil conditional diffusion models with classifier-free guidance: A sharp statistical theory. arXiv preprint arXiv:2403.11968","author":"Fu Hengyu","year":"2024","unstructured":"Hengyu Fu, Zhuoran Yang, Mengdi Wang, and Minshuo Chen. 2024. Unveil conditional diffusion models with classifier-free guidance: A sharp statistical theory. arXiv preprint arXiv:2403.11968 (2024)."},{"key":"e_1_3_2_1_11_1","volume-title":"International conference on machine learning. PMLR","author":"Fujimoto Scott","year":"2019","unstructured":"Scott Fujimoto, David Meger, and Doina Precup. 2019. Off-policy deep reinforcement learning without exploration. In International conference on machine learning. PMLR, 2052--2062."},{"key":"e_1_3_2_1_12_1","unstructured":"Jingtong Gao Yewen Li Shuai Mao Peng Jiang Nan Jiang Yejing Wang Qingpeng Cai Fei Pan Kun Gai Bo An et al. 2025. Generative Auto-Bidding with Value-Guided Explorations. arXiv preprint arXiv:2504.14587 (2025)."},{"key":"e_1_3_2_1_13_1","volume-title":"AIGB: Generative Auto-bidding via Diffusion Modeling. arXiv preprint arXiv:2405.16141","author":"Guo Jiayan","year":"2024","unstructured":"Jiayan Guo, Yusen Huo, Zhilin Zhang, Tianyu Wang, Chuan Yu, Jian Xu, Yan Zhang, and Bo Zheng. 2024. AIGB: Generative Auto-bidding via Diffusion Modeling. arXiv preprint arXiv:2405.16141 (2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671526"},{"key":"e_1_3_2_1_15_1","volume-title":"Jakub Grudzien Kuba, and Sergey Levine","author":"Hansen-Estruch Philippe","year":"2023","unstructured":"Philippe Hansen-Estruch, Ilya Kostrikov, Michael Janner, Jakub Grudzien Kuba, and Sergey Levine. 2023. Idql: Implicit q-learning as an actor-critic method with diffusion policies. arXiv preprint arXiv:2304.10573 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3447548.3467199"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1395"},{"key":"e_1_3_2_1_18_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems 33","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_19_1","volume-title":"Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)."},{"key":"e_1_3_2_1_20_1","volume-title":"Dual Conditional Diffusion Models for Sequential Recommendation. arXiv preprint arXiv:2410.21967","author":"Huang Hongtao","year":"2024","unstructured":"Hongtao Huang, Chengkai Huang, Xiaojun Chang, Wen Hu, and Lina Yao. 2024. Dual Conditional Diffusion Models for Sequential Recommendation. arXiv preprint arXiv:2410.21967 (2024)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3272021"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2019.1198"},{"key":"e_1_3_2_1_23_1","volume-title":"Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114","author":"Kingma Diederik P","year":"2013","unstructured":"Diederik P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)."},{"key":"e_1_3_2_1_24_1","unstructured":"Ilya Kostrikov Ashvin Nair and Sergey Levine. 2022. Offline Reinforcement Learning with Implicit Q-Learning. In ICLR."},{"key":"e_1_3_2_1_25_1","unstructured":"Aviral Kumar Aurick Zhou George Tucker and Sergey Levine. 2020. Conservative Q-Learning for Offline Reinforcement Learning. In NeurIPS."},{"key":"e_1_3_2_1_26_1","volume-title":"EBaReT: Expert-guided Bag Reward Transformer for Auto Bidding. In Companion Proceedings of the ACM on Web Conference","author":"Li Kaiyuan","year":"2025","unstructured":"Kaiyuan Li, Pengyu Wang, Yunshan Peng, Pengjia Yuan, Yanxiang Zeng, Rui Xiang, Yanhua Cheng, Xialong Liu, and Peng Jiang. 2025. EBaReT: Expert-guided Bag Reward Transformer for Auto Bidding. In Companion Proceedings of the ACM on Web Conference 2025. 1104--1108."},{"key":"e_1_3_2_1_27_1","volume-title":"GAS: Generative Auto-bidding with Post-training Search. arXiv preprint arXiv:2412.17018","author":"Li Yewen","year":"2024","unstructured":"Yewen Li, Shuai Mao, Jingtong Gao, Nan Jiang, Yunjian Xu, Qingpeng Cai, Fei Pan, Peng Jiang, and Bo An. 2024. GAS: Generative Auto-bidding with Post-training Search. arXiv preprint arXiv:2412.17018 (2024)."},{"key":"e_1_3_2_1_28_1","first-page":"1","article-title":"Diffurec: A diffusion model for sequential recommendation","volume":"42","author":"Li Zihao","year":"2023","unstructured":"Zihao Li, Aixin Sun, and Chenliang Li. 2023. Diffurec: A diffusion model for sequential recommendation. ACM Transactions on Information Systems 42, 3 (2023), 1--28.","journal-title":"ACM Transactions on Information Systems"},{"key":"e_1_3_2_1_29_1","volume-title":"International Conference on Machine Learning. PMLR, 21127--21152","author":"Lin Qian","year":"2023","unstructured":"Qian Lin, Bo Tang, Zifan Wu, Chao Yu, Shangqin Mao, Qianlong Xie, Xingxing Wang, and Dong Wang. 2023. Safe offline reinforcement learning with realtime budget constraints. In International Conference on Machine Learning. PMLR, 21127--21152."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671729"},{"key":"e_1_3_2_1_31_1","first-page":"2651","article-title":"Sustainable online reinforcement learning for auto-bidding","volume":"35","author":"Mou Zhiyu","year":"2022","unstructured":"Zhiyu Mou, Yusen Huo, Rongquan Bai, Mingzhou Xie, Chuan Yu, Jian Xu, and Bo Zheng. 2022. Sustainable online reinforcement learning for auto-bidding. Advances in Neural Information Processing Systems 35 (2022), 2651--2663.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_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_33_1","unstructured":"Tianchi. 2024. AIGB Track: Learning Auto-Bidding Agent with Generative Models. https:\/\/tianchi.aliyun.com\/competition\/entrance\/532236\/customize448?lang=en-us"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"crossref","unstructured":"Faraz Torabi Garrett Warnell and Peter Stone. 2018. Behavioral Cloning from Observation. In IJCAI J\u00e9r\u00f4me Lang (Ed.). 4950--4957.","DOI":"10.24963\/ijcai.2018\/687"},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Lukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Jun Wang Weinan Zhang Shuai Yuan et al. 2017. Display advertising with real-time bidding (RTB) and behavioural targeting. Foundations and Trends\u00ae in Information Retrieval 11 4--5 (2017) 297--435.","DOI":"10.1561\/1500000049"},{"key":"e_1_3_2_1_37_1","volume-title":"Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 156--169","author":"Liu Zhiwei","year":"2024","unstructured":"YuWang, Zhiwei Liu, Liangwei Yang, and Philip S Yu. 2024. Conditional denoising diffusion for sequential recommendation. In Pacific-Asia Conference on Knowledge Discovery and Data Mining. Springer, 156--169."},{"key":"e_1_3_2_1_38_1","volume-title":"Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv preprint arXiv:2208.06193","author":"Wang Zhendong","year":"2022","unstructured":"Zhendong Wang, Jonathan J Hunt, and Mingyuan Zhou. 2022. Diffusion policies as an expressive policy class for offline reinforcement learning. arXiv preprint arXiv:2208.06193 (2022)."},{"key":"e_1_3_2_1_39_1","volume-title":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 1129--1139","author":"Xu Miao","year":"2022","unstructured":"ChaoWen, Miao Xu, Zhilin Zhang, Zhenzhe Zheng, YuhuiWang, Xiangyu Liu, Yu Rong, Dong Xie, Xiaoyang Tan, Chuan Yu, et al. 2022. A cooperative-competitive multi-agent framework for auto-bidding in online advertising. In Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining. 1129--1139."},{"key":"e_1_3_2_1_40_1","volume-title":"A learning algorithm for continually running fully recurrent neural networks. Neural computation 1, 2","author":"Williams Ronald J","year":"1989","unstructured":"Ronald J Williams and David Zipser. 1989. A learning algorithm for continually running fully recurrent neural networks. Neural computation 1, 2 (1989), 270--280."},{"key":"e_1_3_2_1_41_1","volume-title":"Generate what you prefer: Reshaping sequential recommendation via guided diffusion. Advances in Neural Information Processing Systems 36","author":"Yang Zhengyi","year":"2024","unstructured":"Zhengyi Yang, Jiancan Wu, Zhicai Wang, Xiang Wang, Yancheng Yuan, and Xiangnan He. 2024. Generate what you prefer: Reshaping sequential recommendation via guided diffusion. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501040.2501980"},{"key":"e_1_3_2_1_43_1","volume-title":"Diffusion models for reinforcement learning: A survey. arXiv preprint arXiv:2311.01223","author":"Zhu Zhengbang","year":"2023","unstructured":"Zhengbang Zhu, Hanye Zhao, Haoran He, Yichao Zhong, Shenyu Zhang, Haoquan Guo, Tingting Chen, and Weinan Zhang. 2023. Diffusion models for reinforcement learning: A survey. arXiv preprint arXiv:2311.01223 (2023)."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Seoul Republic of Korea","acronym":"CIKM '25"},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T00:23:26Z","timestamp":1765499006000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761497"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":43,"alternative-id":["10.1145\/3746252.3761497","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761497","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}