{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:30:30Z","timestamp":1765308630187,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":32,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755441","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:50:47Z","timestamp":1761371447000},"page":"10152-10160","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Text2Weight: Bridging Natural Language and Neural Network Weight Spaces"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1305-3097","authenticated-orcid":false,"given":"Bowen","family":"Tian","sequence":"first","affiliation":[{"name":"Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1966-6059","authenticated-orcid":false,"given":"Wenshuo","family":"Chen","sequence":"additional","affiliation":[{"name":"Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0831-3549","authenticated-orcid":false,"given":"Zexi","family":"Li","sequence":"additional","affiliation":[{"name":"The University of Cambridge, Cambridge, United Kingdom and Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3132-9414","authenticated-orcid":false,"given":"Songning","family":"Lai","sequence":"additional","affiliation":[{"name":"Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2712-4876","authenticated-orcid":false,"given":"Jiemin","family":"Wu","sequence":"additional","affiliation":[{"name":"Deep Interdisciplinary Intelligence Lab, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4532-0924","authenticated-orcid":false,"given":"Yutao","family":"Yue","sequence":"additional","affiliation":[{"name":"Thrust of Artificial Intelligence and Thrust of Intelligent Transportation, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China and Institute of Deep Perception Technology, Jiangsu Industrial Technology Research Institute, Wuxi, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Git re-basin: Merging models modulo permutation symmetries. arXiv preprint arXiv:2209.04836","author":"Ainsworth Samuel K","year":"2022","unstructured":"Samuel K Ainsworth, Jonathan Hayase, and Siddhartha Srinivasa. 2022. Git re-basin: Merging models modulo permutation symmetries. arXiv preprint arXiv:2209.04836 (2022)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Zal\u00e1n Borsos Rapha\u00ebl Marinier Damien Vincent Eugene Kharitonov Olivier Pietquin Matt Sharifi Dominik Roblek Olivier Teboul David Grangier Marco Tagliasacchi et al. 2023. Audiolm: a language modeling approach to audio generation. IEEE\/ACM transactions on audio speech and language processing Vol. 31 (2023) 2523-2533.","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249-256","author":"Glorot Xavier","year":"2010","unstructured":"Xavier Glorot and Yoshua Bengio. 2010. Understanding the difficulty of training deep feedforward neural networks. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. JMLR Workshop and Conference Proceedings, 249-256."},{"key":"e_1_3_2_1_4_1","volume-title":"Efficient Training with Denoised Neural Weights. In European Conference on Computer Vision. Springer, 18-34","author":"Gong Yifan","year":"2024","unstructured":"Yifan Gong, Zheng Zhan, Yanyu Li, Yerlan Idelbayev, Andrey Zharkov, Kfir Aberman, Sergey Tulyakov, Yanzhi Wang, and Jian Ren. 2024. Efficient Training with Denoised Neural Weights. In European Conference on Computer Vision. Springer, 18-34."},{"key":"e_1_3_2_1_5_1","unstructured":"Gregory Griffin Alex Holub and Pietro Perona. 2007. Caltech-256 object category dataset. (2007)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_8_1","volume-title":"Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi.","author":"Ilharco Gabriel","year":"2022","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Suchin Gururangan, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2022. Editing models with task arithmetic. arXiv preprint arXiv:2212.04089 (2022)."},{"key":"e_1_3_2_1_9_1","volume-title":"Conditional lora parameter generation. arXiv preprint arXiv:2408.01415","author":"Jin Xiaolong","year":"2024","unstructured":"Xiaolong Jin, Kai Wang, Dongwen Tang, Wangbo Zhao, Yukun Zhou, Junshu Tang, and Yang You. 2024. Conditional lora parameter generation. arXiv preprint arXiv:2408.01415 (2024)."},{"key":"e_1_3_2_1_10_1","volume-title":"Audiogen: Textually guided audio generation. arXiv preprint arXiv:2209.15352","author":"Kreuk Felix","year":"2022","unstructured":"Felix Kreuk, Gabriel Synnaeve, Adam Polyak, Uriel Singer, Alexandre D\u00e9fossez, Jade Copet, Devi Parikh, Yaniv Taigman, and Yossi Adi. 2022. Audiogen: Textually guided audio generation. arXiv preprint arXiv:2209.15352 (2022)."},{"key":"e_1_3_2_1_11_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images.(2009)."},{"key":"e_1_3_2_1_12_1","volume-title":"Visualizing the loss landscape of neural nets. Advances in neural information processing systems","author":"Li Hao","year":"2018","unstructured":"Hao Li, Zheng Xu, Gavin Taylor, Christoph Studer, and Tom Goldstein. 2018. Visualizing the loss landscape of neural nets. Advances in neural information processing systems, Vol. 31 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Text-to-model: Text-conditioned neural network diffusion for train-once-for-all personalization. arXiv preprint arXiv:2405.14132","author":"Li Zexi","year":"2024","unstructured":"Zexi Li, Lingzhi Gao, and Chao Wu. 2024. Text-to-model: Text-conditioned neural network diffusion for train-once-for-all personalization. arXiv preprint arXiv:2405.14132 (2024)."},{"key":"e_1_3_2_1_14_1","volume-title":"Graph metanetworks for processing diverse neural architectures. arXiv preprint arXiv:2312.04501","author":"Lim Derek","year":"2023","unstructured":"Derek Lim, Haggai Maron, Marc T Law, Jonathan Lorraine, and James Lucas. 2023. Graph metanetworks for processing diverse neural architectures. arXiv preprint arXiv:2312.04501 (2023)."},{"key":"e_1_3_2_1_15_1","unstructured":"mnmoustafa and Mohammed Ali. 2017. Tiny ImageNet. https:\/\/kaggle.com\/competitions\/tiny-imagenet. Kaggle."},{"key":"e_1_3_2_1_16_1","volume-title":"Meta-learning via classifier (-free) diffusion guidance. arXiv preprint arXiv:2210.08942","author":"Nava Elvis","year":"2022","unstructured":"Elvis Nava, Seijin Kobayashi, Yifei Yin, Robert K Katzschmann, and Benjamin F Grewe. 2022. Meta-learning via classifier (-free) diffusion guidance. arXiv preprint arXiv:2210.08942 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"International Conference on Machine Learning. PMLR, 25790-25816","author":"Navon Aviv","year":"2023","unstructured":"Aviv Navon, Aviv Shamsian, Idan Achituve, Ethan Fetaya, Gal Chechik, and Haggai Maron. 2023. Equivariant architectures for learning in deep weight spaces. In International Conference on Machine Learning. PMLR, 25790-25816."},{"key":"e_1_3_2_1_18_1","volume-title":"Learning to learn with generative models of neural network checkpoints. arXiv preprint arXiv:2209.12892","author":"Peebles William","year":"2022","unstructured":"William Peebles, Ilija Radosavovic, Tim Brooks, Alexei A Efros, and Jitendra Malik. 2022. Learning to learn with generative models of neural network checkpoints. arXiv preprint arXiv:2209.12892 (2022)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"e_1_3_2_1_20_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_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_22_1","first-page":"27906","article-title":"Hyper-representations as generative models: Sampling unseen neural network weights","volume":"35","author":"Sch\u00fcrholt Konstantin","year":"2022","unstructured":"Konstantin Sch\u00fcrholt, Boris Knyazev, Xavier Gir\u00f3-i Nieto, and Damian Borth. 2022. Hyper-representations as generative models: Sampling unseen neural network weights. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27906-27920.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_23_1","first-page":"16481","article-title":"Self-supervised representation learning on neural network weights for model characteristic prediction","volume":"34","author":"Sch\u00fcrholt Konstantin","year":"2021","unstructured":"Konstantin Sch\u00fcrholt, Dimche Kostadinov, and Damian Borth. 2021. Self-supervised representation learning on neural network weights for model characteristic prediction. Advances in Neural Information Processing Systems, Vol. 34 (2021), 16481-16493.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_2_1_25_1","volume-title":"Diffusion-based neural network weights generation. arXiv preprint arXiv:2402.18153","author":"Soro Bedionita","year":"2024","unstructured":"Bedionita Soro, Bruno Andreis, Hayeon Lee, Wonyong Jeong, Song Chong, Frank Hutter, and Sung Ju Hwang. 2024. Diffusion-based neural network weights generation. arXiv preprint arXiv:2402.18153 (2024)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889037"},{"key":"e_1_3_2_1_27_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_28_1","volume-title":"Deep learning for computer vision: A brief review. Computational intelligence and neuroscience","author":"Voulodimos Athanasios","year":"2018","unstructured":"Athanasios Voulodimos, Nikolaos Doulamis, Anastasios Doulamis, and Eftychios Protopapadakis. 2018. Deep learning for computer vision: A brief review. Computational intelligence and neuroscience, Vol. 2018, 1 (2018), 7068349."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of the 31st International Conference on Computational Linguistics. 10660-10671","author":"Wang Yihang","year":"2025","unstructured":"Yihang Wang, Bowen Tian, Yueyang Su, Yixing Fan, and Jiafeng Guo. 2025. MDPO: Customized Direct Preference Optimization with a Metric-based Sampler for Question and Answer Generation. In Proceedings of the 31st International Conference on Computational Linguistics. 10660-10671."},{"key":"e_1_3_2_1_30_1","volume-title":"Difflora: Generating personalized low-rank adaptation weights with diffusion. arXiv preprint arXiv:2408.06740","author":"Wu Yujia","year":"2024","unstructured":"Yujia Wu, Yiming Shi, Jiwei Wei, Chengwei Sun, Yang Yang, and Heng Tao Shen. 2024. Difflora: Generating personalized low-rank adaptation weights with diffusion. arXiv preprint arXiv:2408.06740 (2024)."},{"key":"e_1_3_2_1_31_1","first-page":"6367","article-title":"Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments","volume":"37","author":"Xie Mixue","year":"2024","unstructured":"Mixue Xie, Shuang Li, Binhui Xie, Chi Liu, Jian Liang, Zixun Sun, Ke Feng, and Chengwei Zhu. 2024. Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments. Advances in Neural Information Processing Systems, Vol. 37 (2024), 6367-6392.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_32_1","volume-title":"Permutation equivariant neural functionals. Advances in neural information processing systems","author":"Zhou Allan","year":"2023","unstructured":"Allan Zhou, Kaien Yang, Kaylee Burns, Adriano Cardace, Yiding Jiang, Samuel Sokota, J Zico Kolter, and Chelsea Finn. 2023. Permutation equivariant neural functionals. Advances in neural information processing systems, Vol. 36 (2023), 24966-24992."}],"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\/3746027.3755441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:25:56Z","timestamp":1765308356000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":32,"alternative-id":["10.1145\/3746027.3755441","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755441","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"}}]}}