{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T21:13:48Z","timestamp":1788556428777,"version":"build-2803163510"},"publisher-location":"New York, NY, USA","reference-count":40,"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 Science and Technology Council of Taiwan","award":["NSTC 114-2221-E-002-126-MY3"],"award-info":[{"award-number":["NSTC 114-2221-E-002-126-MY3"]}]},{"name":"National Science and Technology Council of Taiwan","award":["NSTC 114-2628-E-002-013-MY3"],"award-info":[{"award-number":["NSTC 114-2628-E-002-013-MY3"]}]},{"name":"Google Asia Pacific","award":["n.a."],"award-info":[{"award-number":["n.a."]}]},{"name":"The Ministry of Education of Taiwan","award":["n.a."],"award-info":[{"award-number":["n.a."]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3818078","type":"proceedings-article","created":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:08:33Z","timestamp":1786064913000},"page":"321-330","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2791-6771","authenticated-orcid":false,"given":"Chih-Heng","family":"Chang","sequence":"first","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-0085-4663","authenticated-orcid":false,"given":"Keng-Seng","family":"Ho","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9524-2480","authenticated-orcid":false,"given":"Chih-Yu","family":"Tsai","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0491-5713","authenticated-orcid":false,"given":"Kuan-Lin","family":"Chen","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2350-8080","authenticated-orcid":false,"given":"Yi-Hsuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4510-2273","authenticated-orcid":false,"given":"Jian-Jiun","family":"Ding","sequence":"additional","affiliation":[{"name":"Graduate Institute of Communication Engineering, National Taiwan University, Taipei, Taiwan"}],"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":"10.52202\/075280-2066"},{"key":"e_1_3_2_1_2_1","volume-title":"High fidelity neural audio compression. arXiv preprint arXiv:2210.13438","author":"D\u00e9fossez Alexandre","year":"2022","unstructured":"Alexandre D\u00e9fossez, Jade Copet, Gabriel Synnaeve, and Yossi Adi. 2022. High fidelity neural audio compression. arXiv preprint arXiv:2210.13438 (2022)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888461"},{"key":"e_1_3_2_1_5_1","volume-title":"Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video. arXiv preprint arXiv:2511.00103","author":"Ezra Rotem","year":"2025","unstructured":"Rotem Ezra, Hedi Zisling, Nimrod Berman, Ilan Naiman, Alexey Gorkor, Liran Nochumsohn, Eliya Nachmani, and Omri Azencot. 2025. FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video. arXiv preprint arXiv:2511.00103 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/FG59268.2024.10581912"},{"key":"e_1_3_2_1_7_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_8_1","volume-title":"International conference on machine learning. PMLR, 2790--2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790--2799."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2081"},{"key":"e_1_3_2_1_10_1","volume-title":"Taming visually guided sound generation. arXiv preprint arXiv:2110.08791","author":"Iashin Vladimir","year":"2021","unstructured":"Vladimir Iashin and Esa Rahtu. 2021. Taming visually guided sound generation. arXiv preprint arXiv:2110.08791 (2021)."},{"key":"e_1_3_2_1_11_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_1_12_1","volume-title":"Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960","author":"Kwon Mingi","year":"2022","unstructured":"Mingi Kwon, Jaeseok Jeong, and Youngjung Uh. 2022. Diffusion models already have a semantic latent space. arXiv preprint arXiv:2210.10960 (2022)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12006--12016","author":"Li Hang","year":"2024","unstructured":"Hang Li, Chengzhi Shen, Philip Torr, Volker Tresp, and Jindong Gu. 2024. Selfdiscovering interpretable diffusion latent directions for responsible text-to-image generation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12006--12016."},{"key":"e_1_3_2_1_14_1","volume-title":"A technique for the measurement of attitudes. Archives of psychology","author":"Likert Rensis","year":"1932","unstructured":"Rensis Likert. 1932. A technique for the measurement of attitudes. Archives of psychology (1932)."},{"key":"e_1_3_2_1_15_1","volume-title":"Medic: Zero-shot music editing with disentangled inversion control. arXiv preprint arXiv:2407.13220","author":"Liu Huadai","year":"2024","unstructured":"Huadai Liu, Jialei Wang, Xiangtai Li, Wen Wang, Qian Chen, Rongjie Huang, Yang Liu, Jiayang Xu, and Zhou Zhao. 2024. Medic: Zero-shot music editing with disentangled inversion control. arXiv preprint arXiv:2407.13220 (2024)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"e_1_3_2_1_17_1","volume-title":"Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983","author":"Loshchilov Ilya","year":"2016","unstructured":"Ilya Loshchilov and Frank Hutter. 2016. Sgdr: Stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)."},{"key":"e_1_3_2_1_18_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_19_1","volume-title":"Zero-shot unsupervised and text-based audio editing using DDPM inversion. arXiv preprint arXiv:2402.10009","author":"Manor Hila","year":"2024","unstructured":"Hila Manor and Tomer Michaeli. 2024. Zero-shot unsupervised and text-based audio editing using DDPM inversion. arXiv preprint arXiv:2402.10009 (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073","author":"Meng Chenlin","year":"2021","unstructured":"Chenlin Meng, Yutong He, Yang Song, Jiaming Song, JiajunWu, Jun-Yan Zhu, and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:2108.01073 (2021)."},{"key":"e_1_3_2_1_21_1","volume-title":"Zhepei Wang, Mirco Ravanelli","author":"Paissan Francesco","year":"2023","unstructured":"Francesco Paissan, Luca Della Libera, Zhepei Wang, Mirco Ravanelli, Paris Smaragdis, and Cem Subakan. 2023. Audio editing with non-rigid text prompts. arXiv preprint arXiv:2310.12858 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems 32 (2019)."},{"key":"e_1_3_2_1_23_1","volume-title":"Is disentanglement enough? On latent representations for controllable music generation. arXiv preprint arXiv:2108.01450","author":"Pati Ashis","year":"2021","unstructured":"Ashis Pati and Alexander Lerch. 2021. Is disentanglement enough? On latent representations for controllable music generation. arXiv preprint arXiv:2108.01450 (2021)."},{"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","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research 21, 140 (2020), 1--67.","journal-title":"Journal of machine learning research"},{"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","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"e_1_3_2_1_29_1","volume-title":"Audio prompt adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning. arXiv preprint arXiv:2407.16564","author":"Tsai Fang-Duo","year":"2024","unstructured":"Fang-Duo Tsai, Shih-Lun Wu, Haven Kim, Bo-Yu Chen, Hao-Chung Cheng, and Yi-Hsuan Yang. 2024. Audio prompt adapter: Unleashing music editing abilities for text-to-music with lightweight finetuning. arXiv preprint arXiv:2407.16564 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners. arXiv preprint arXiv:2506.18729","author":"Tsai Fang-Duo","year":"2025","unstructured":"Fang-Duo Tsai, Shih-Lun Wu, Weijaw Lee, Sheng-Ping Yang, Bo-Rui Chen, Hao-Chung Cheng, and Yi-Hsuan Yang. 2025. MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners. arXiv preprint arXiv:2506.18729 (2025)."},{"key":"e_1_3_2_1_31_1","unstructured":"Aaron Van Den Oord Oriol Vinyals et al. 2017. Neural discrete representation learning. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_32_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, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_33_1","volume-title":"Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers.","author":"von Platen Patrick","year":"2022","unstructured":"Patrick von Platen, Suraj Patil, Anton Lozhkov, Pedro Cuenca, Nathan Lambert, Kashif Rasul, Mishig Davaadorj, Dhruv Nair, Sayak Paul, William Berman, Yiyi Xu, Steven Liu, and Thomas Wolf. 2022. Diffusers: State-of-the-art diffusion models. https:\/\/github.com\/huggingface\/diffusers."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399026"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"e_1_3_2_1_36_1","volume-title":"Deep music analogy via latent representation disentanglement. arXiv preprint arXiv:1906.03626","author":"Yang Ruihan","year":"2019","unstructured":"Ruihan Yang, Dingsu Wang, Ziyu Wang, Tianyao Chen, Junyan Jiang, and Gus Xia. 2019. Deep music analogy via latent representation disentanglement. arXiv preprint arXiv:1906.03626 (2019)."},{"key":"e_1_3_2_1_37_1","volume-title":"Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models. arXiv preprint arXiv:2511.08252","author":"Yang Yi","year":"2025","unstructured":"Yi Yang, Haowen Li, Tianxiang Li, Boyu Cao, Xiaohan Zhang, Liqun Chen, and Qi Liu. 2025. Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models. arXiv preprint arXiv:2511.08252 (2025)."},{"key":"e_1_3_2_1_38_1","volume-title":"Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training. arXiv preprint arXiv:2512.02652","author":"You Hong-Jie","year":"2025","unstructured":"Hong-Jie You, Jie-Jing Shao, Xiao-Wen Yang, Lin-Han Jia, Lan-Zhe Guo, and Yu-Feng Li. 2025. Pianist Transformer: Towards Expressive Piano Performance Rendering via Scalable Self-Supervised Pre-Training. arXiv preprint arXiv:2512.02652 (2025)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_40_1","volume-title":"Musicmagus: Zero-shot text-to-music editing via diffusion models. arXiv preprint arXiv:2402.06178","author":"Zhang Yixiao","year":"2024","unstructured":"Yixiao Zhang, Yukara Ikemiya, Gus Xia, Naoki Murata, Marco A Mart\u00ednez-Ram\u00edrez, Wei-Hsiang Liao, Yuki Mitsufuji, and Simon Dixon. 2024. Musicmagus: Zero-shot text-to-music editing via diffusion models. arXiv preprint arXiv:2402.06178 (2024)."}],"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":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770855.3818078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T20:33:27Z","timestamp":1788554007000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":40,"alternative-id":["10.1145\/3770855.3818078","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818078","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"}}]}}