{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:05:29Z","timestamp":1784228729077,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T00:00:00Z","timestamp":1784419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Research Grants Council, Hong Kong - Theme-based Research Scheme","award":["T45-205\/21-N"],"award-info":[{"award-number":["T45-205\/21-N"]}]},{"name":"Research Grants Council, Hong Kong - Early Career Scheme","award":["22201322"],"award-info":[{"award-number":["22201322"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7,19]]},"DOI":"10.1145\/3799902.3811191","type":"proceedings-article","created":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T16:15:27Z","timestamp":1784218527000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7278-3708","authenticated-orcid":false,"given":"Zeyue","family":"Tian","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4110-1986","authenticated-orcid":false,"given":"Binxin","family":"Yang","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0258-3097","authenticated-orcid":false,"given":"Zhaoyang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8609-8919","authenticated-orcid":false,"given":"Jiexuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0539-6916","authenticated-orcid":false,"given":"Ruibin","family":"Yuan","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-9492-8729","authenticated-orcid":false,"given":"Hubery","family":"Yin","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2199-3948","authenticated-orcid":false,"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2450-8525","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2021-0256","authenticated-orcid":false,"given":"Jing","family":"Lyu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4942-7748","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8401-282X","authenticated-orcid":false,"given":"Yike","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,19]]},"reference":[{"key":"e_1_3_3_3_2_1","unstructured":"Inclusion AI Biao Gong Cheng Zou Chuanyang Zheng Chunluan Zhou Canxiang Yan Chunxiang Jin Chunjie Shen Dandan Zheng Fudong Wang et\u00a0al. 2025. Ming-Omni: A Unified Multimodal Model for Perception and Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.09344 (2025)."},{"key":"e_1_3_3_3_3_1","unstructured":"Keyu An Qian Chen Chong Deng Zhihao Du Changfeng Gao Zhifu Gao Yue Gu Ting He Hangrui Hu Kai Hu et\u00a0al. 2024. Funaudiollm: Voice understanding and generation foundation models for natural interaction between humans and llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.04051 (2024)."},{"key":"e_1_3_3_3_4_1","unstructured":"Philip Anastassiou Jiawei Chen Jitong Chen Yuanzhe Chen Zhuo Chen Ziyi Chen Jian Cong Lelai Deng Chuang Ding Lu Gao et\u00a0al. 2024. Seed-tts: A family of high-quality versatile speech generation models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.02430 (2024)."},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"e_1_3_3_3_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"e_1_3_3_3_7_1","unstructured":"Xiaokang Chen Zhiyu Wu Xingchao Liu Zizheng Pan Wen Liu Zhenda Xie Xingkai Yu and Chong Ruan. 2025b. Janus-pro: Unified multimodal understanding and generation with data and model scaling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.17811 (2025)."},{"key":"e_1_3_3_3_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02691"},{"key":"e_1_3_3_3_10_1","unstructured":"Yunfei Chu Jin Xu Qian Yang Haojie Wei Xipin Wei Zhifang Guo Yichong Leng Yuanjun Lv Jinzheng He Junyang Lin et\u00a0al. 2024. Qwen2-audio technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.10759 (2024)."},{"key":"e_1_3_3_3_11_1","unstructured":"Yunfei Chu Jin Xu Xiaohuan Zhou Qian Yang Shiliang Zhang Zhijie Yan Chang Zhou and Jingren Zhou. 2023. Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.07919 (2023)."},{"key":"e_1_3_3_3_12_1","doi-asserted-by":"crossref","unstructured":"Jade Copet Felix Kreuk Itai Gat Tal Remez David Kant Gabriel Synnaeve Yossi Adi and Alexandre D\u00e9fossez. 2024. Simple and controllable music generation. Advances in Neural Information Processing Systems 36 (2024).","DOI":"10.52202\/075280-2066"},{"key":"e_1_3_3_3_13_1","unstructured":"Qixin Deng Qikai Yang Ruibin Yuan Yipeng Huang Yi Wang Xubo Liu Zeyue Tian Jiahao Pan Ge Zhang Hanfeng Lin et\u00a0al. 2024. Composerx: Multi-agent symbolic music composition with llms. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.18081 (2024)."},{"key":"e_1_3_3_3_14_1","unstructured":"Wei Deng Siyi Zhou Jingchen Shu Jinchao Wang and Lu Wang. 2025. Indextts: An industrial-level controllable and efficient zero-shot text-to-speech system. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2502.05512 (2025)."},{"key":"e_1_3_3_3_15_1","unstructured":"Zhihao Du Qian Chen Shiliang Zhang Kai Hu Heng Lu Yexin Yang Hangrui Hu Siqi Zheng Yue Gu Ziyang Ma et\u00a0al. 2024. Cosyvoice: A scalable multilingual zero-shot text-to-speech synthesizer based on supervised semantic tokens. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.05407 (2024)."},{"key":"e_1_3_3_3_16_1","unstructured":"Zhihao Du Changfeng Gao Yuxuan Wang Fan Yu Tianyu Zhao Hao Wang Xiang Lv Hui Wang Chongjia Ni Xian Shi et\u00a0al. 2025. Cosyvoice 3: Towards in-the-wild speech generation via scaling-up and post-training. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.17589 (2025)."},{"key":"e_1_3_3_3_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"e_1_3_3_3_18_1","unstructured":"Zach Evans Julian\u00a0D Parker CJ Carr Zack Zukowski Josiah Taylor and Jordi Pons. 2024. Stable audio open. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.14358 (2024)."},{"key":"e_1_3_3_3_19_1","doi-asserted-by":"crossref","unstructured":"Deepanway Ghosal Navonil Majumder Ambuj Mehrish and Soujanya Poria. 2023. Text-to-audio generation using instruction-tuned llm and latent diffusion model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.13731 (2023).","DOI":"10.1145\/3581783.3612348"},{"key":"e_1_3_3_3_20_1","volume-title":"Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025","author":"Ghosh Sreyan","year":"2025","unstructured":"Sreyan Ghosh, Zhifeng Kong, Sonal Kumar, S. Sakshi, Jaehyeon Kim, Wei Ping, Rafael Valle, Dinesh Manocha, and Bryan Catanzaro. 2025. Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities. In Forty-second International Conference on Machine Learning, ICML 2025, Vancouver, BC, Canada, July 13-19, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=xWu5qpDK6U"},{"key":"e_1_3_3_3_21_1","unstructured":"Arushi Goel Sreyan Ghosh Jaehyeon Kim Sonal Kumar Zhifeng Kong Sang-gil Lee Chao-Han\u00a0Huck Yang Ramani Duraiswami Dinesh Manocha Rafael Valle et\u00a0al. 2025. Audio flamingo 3: Advancing audio intelligence with fully open large audio language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2507.08128 (2025)."},{"key":"e_1_3_3_3_22_1","unstructured":"Yingqing He Zhaoyang Liu Jingye Chen Zeyue Tian Hongyu Liu Xiaowei Chi Runtao Liu Ruibin Yuan Yazhou Xing Wenhai Wang et\u00a0al. 2024. Llms meet multimodal generation and editing: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.19334 (2024)."},{"key":"e_1_3_3_3_23_1","unstructured":"Jiawei Huang Yi Ren Rongjie Huang Dongchao Yang Zhenhui Ye Chen Zhang Jinglin Liu Xiang Yin Zejun Ma and Zhou Zhao. 2023. Make-an-audio 2: Temporal-enhanced text-to-audio generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.18474 (2023)."},{"key":"e_1_3_3_3_24_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"e_1_3_3_3_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i21.30570"},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"e_1_3_3_3_27_1","unstructured":"Siyu Jiao Yiheng Lin Yujie Zhong Qi She Wei Zhou Xiaohan Lan Zilong Huang Fei Yu Yingchen Yu Yunqing Zhao et\u00a0al. 2025. ThinkGen: Generalized Thinking for Visual Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.23568 (2025)."},{"key":"e_1_3_3_3_28_1","first-page":"119","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Kim Chris\u00a0Dongjoo","year":"2019","unstructured":"Chris\u00a0Dongjoo Kim, Byeongchang Kim, Hyunmin Lee, and Gunhee Kim. 2019. Audiocaps: Generating captions for audios in the wild. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 119\u2013132."},{"key":"e_1_3_3_3_29_1","doi-asserted-by":"crossref","unstructured":"Qiuqiang Kong Yin Cao Turab Iqbal Yuxuan Wang Wenwu Wang and Mark\u00a0D Plumbley. 2020. Panns: Large-scale pretrained audio neural networks for audio pattern recognition. IEEE\/ACM Transactions on Audio Speech and Language Processing 28 (2020) 2880\u20132894.","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"e_1_3_3_3_30_1","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","author":"Kong Zhifeng","year":"2024","unstructured":"Zhifeng Kong, Arushi Goel, Rohan Badlani, Wei Ping, Rafael Valle, and Bryan Catanzaro. 2024. Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities. In Forty-first International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=WYi3WKZjYe"},{"key":"e_1_3_3_3_31_1","unstructured":"Zitong Lan Yiduo Hao and Mingmin Zhao. 2025. Guiding audio editing with audio language model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.21625 (2025)."},{"key":"e_1_3_3_3_32_1","unstructured":"Yan-Bo Lin Yu Tian Linjie Yang Gedas Bertasius and Heng Wang. 2024. VMAS: Video-to-Music Generation via Semantic Alignment in Web Music Videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.07450 (2024)."},{"key":"e_1_3_3_3_33_1","unstructured":"Huadai Liu Kaicheng Luo Jialei Wang Wen Wang Qian Chen Zhou Zhao and Wei Xue. 2025c. Thinksound: Chain-of-thought reasoning in multimodal large language models for audio generation and editing. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.21448 (2025)."},{"key":"e_1_3_3_3_34_1","unstructured":"Kai Liu Jungang Li Yuchong Sun Shengqiong Wu Jianzhang Gao Daoan Zhang Wei Zhang Sheng Jin Sicheng Yu Geng Zhan et\u00a0al. 2025a. Javisgpt: A unified multi-modal llm for sounding-video comprehension and generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.22905 (2025)."},{"key":"e_1_3_3_3_35_1","unstructured":"Shansong Liu Atin\u00a0Sakkeer Hussain Qilong Wu Chenshuo Sun and Ying Shan. 2024a. MuMu-LLaMA: Multi-modal Music Understanding and Generation via Large Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.06660 (2024)."},{"key":"e_1_3_3_3_36_1","unstructured":"Xingchao Liu Chengyue Gong and Qiang Liu. 2022. Flow straight and fast: Learning to generate and transfer data with rectified flow. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2209.03003 (2022)."},{"key":"e_1_3_3_3_37_1","unstructured":"Xiulong Liu Kun Su and Eli Shlizerman. 2024b. Tell What You Hear From What You See\u2013Video to Audio Generation Through Text. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.05679 (2024)."},{"key":"e_1_3_3_3_38_1","unstructured":"Zhenyu Liu Yunxin Li Xuanyu Zhang Qixun Teng Shenyuan Jiang Xinyu Chen Haoyuan Shi Jinchao Li Qi Wang Haolan Chen et\u00a0al. 2025b. UniMoE-Audio: Unified Speech and Music Generation with Dynamic-Capacity MoE. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.13344 (2025)."},{"key":"e_1_3_3_3_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02497"},{"key":"e_1_3_3_3_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00725"},{"key":"e_1_3_3_3_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"e_1_3_3_3_42_1","unstructured":"Hila Manor and Tomer Michaeli. 2024. Zero-shot unsupervised and text-based audio editing using DDPM inversion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.10009 (2024)."},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.459"},{"key":"e_1_3_3_3_44_1","unstructured":"Chenlin Meng Yutong He Yang Song Jiaming Song Jiajun Wu Jun-Yan Zhu and Stefano Ermon. 2021. Sdedit: Guided image synthesis and editing with stochastic differential equations. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2108.01073 (2021)."},{"key":"e_1_3_3_3_45_1","unstructured":"Xichen Pan Satya\u00a0Narayan Shukla Aashu Singh Zhuokai Zhao Shlok\u00a0Kumar Mishra Jialiang Wang Zhiyang Xu Jiuhai Chen Kunpeng Li Felix Juefei-Xu et\u00a0al. 2025. Transfer between modalities with metaqueries. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2504.06256 (2025)."},{"key":"e_1_3_3_3_46_1","unstructured":"Puyuan Peng Po-Yao Huang Shang-Wen Li Abdelrahman Mohamed and David Harwath. 2024. Voicecraft: Zero-shot speech editing and text-to-speech in the wild. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.16973 (2024)."},{"key":"e_1_3_3_3_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"e_1_3_3_3_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755758"},{"key":"e_1_3_3_3_49_1","unstructured":"S Sakshi Utkarsh Tyagi Sonal Kumar Ashish Seth Ramaneswaran Selvakumar Oriol Nieto Ramani Duraiswami Sreyan Ghosh and Dinesh Manocha. 2024. Mmau: A massive multi-task audio understanding and reasoning benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.19168 (2024)."},{"key":"e_1_3_3_3_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170052"},{"key":"e_1_3_3_3_51_1","unstructured":"Bowen Shi Andros Tjandra John Hoffman Helin Wang Yi-Chiao Wu Luya Gao Julius Richter Matt Le Apoorv Vyas Sanyuan Chen et\u00a0al. 2025. SAM Audio: Segment Anything in Audio. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.18099 (2025)."},{"key":"e_1_3_3_3_52_1","unstructured":"Kun Su Judith\u00a0Yue Li Qingqing Huang Dima Kuzmin Joonseok Lee Chris Donahue Fei Sha Aren Jansen Yu Wang Mauro Verzetti et\u00a0al. 2023. V2Meow: Meowing to the Visual Beat via Music Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.06594 (2023)."},{"key":"e_1_3_3_3_53_1","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024","author":"Tang Changli","year":"2024","unstructured":"Changli Tang, Wenyi Yu, Guangzhi Sun, Xianzhao Chen, Tian Tan, Wei Li, Lu Lu, Zejun Ma, and Chao Zhang. 2024. SALMONN: Towards Generic Hearing Abilities for Large Language Models. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=14rn7HpKVk"},{"key":"e_1_3_3_3_54_1","unstructured":"Ye Tao Xuenan Xu Wen Wu Shuai Wang Mengyue Wu and Chao Zhang. 2025. MMEDIT: A Unified Framework for Multi-Type Audio Editing via Audio Language Model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2512.20339 (2025)."},{"key":"e_1_3_3_3_55_1","unstructured":"Jinchuan Tian Sang-gil Lee Zhifeng Kong Sreyan Ghosh Arushi Goel Chao-Han\u00a0Huck Yang Wenliang Dai Zihan Liu Hanrong Ye Shinji Watanabe et\u00a0al. 2025b. Ualm: Unified audio language model for understanding generation and reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.12000 (2025)."},{"key":"e_1_3_3_3_56_1","unstructured":"Zeyue Tian Yizhu Jin Zhaoyang Liu Ruibin Yuan Xu Tan Qifeng Chen Wei Xue and Yike Guo. 2025a. Audiox: Diffusion transformer for anything-to-audio generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.10522 (2025)."},{"key":"e_1_3_3_3_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01750"},{"key":"e_1_3_3_3_58_1","unstructured":"Chengyi Wang Sanyuan Chen Yu Wu Ziqiang Zhang Long Zhou Shujie Liu Zhuo Chen Yanqing Liu Huaming Wang Jinyu Li et\u00a0al. 2023a. Neural codec language models are zero-shot text to speech synthesizers. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2301.02111 (2023)."},{"key":"e_1_3_3_3_59_1","unstructured":"Dingdong Wang Jincenzi Wu Junan Li Dongchao Yang Xueyuan Chen Tianhua Zhang and Helen Meng. 2025b. MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2506.04779 (2025)."},{"key":"e_1_3_3_3_60_1","unstructured":"Le Wang Jun Wang Chunyu Qiang Feng Deng Chen Zhang Di Zhang and Kun Gai. 2025a. Audiogen-omni: A unified multimodal diffusion transformer for video-synchronized audio speech and song generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.00733 (2025)."},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"crossref","unstructured":"Yuancheng Wang Zeqian Ju Xu Tan Lei He Zhizheng Wu Jiang Bian et\u00a0al. 2023b. Audit: Audio editing by following instructions with latent diffusion models. Advances in Neural Information Processing Systems 36 (2023) 71340\u201371357.","DOI":"10.52202\/075280-3124"},{"key":"e_1_3_3_3_62_1","unstructured":"Yuancheng Wang Haoyue Zhan Liwei Liu Ruihong Zeng Haotian Guo Jiachen Zheng Qiang Zhang Xueyao Zhang Shunsi Zhang and Zhizheng Wu. 2024. Maskgct: Zero-shot text-to-speech with masked generative codec transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.00750 (2024)."},{"key":"e_1_3_3_3_63_1","unstructured":"Cong Wei Quande Liu Zixuan Ye Qiulin Wang Xintao Wang Pengfei Wan Kun Gai and Wenhu Chen. 2025. Univideo: Unified understanding generation and editing for videos. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2510.08377 (2025)."},{"key":"e_1_3_3_3_64_1","volume-title":"Forty-first International Conference on Machine Learning","author":"Wu Shengqiong","year":"2024","unstructured":"Shengqiong Wu, Hao Fei, Leigang Qu, Wei Ji, and Tat-Seng Chua. 2024. Next-gpt: Any-to-any multimodal llm. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01262"},{"key":"e_1_3_3_3_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"e_1_3_3_3_67_1","unstructured":"Jin Xu Zhifang Guo Jinzheng He Hangrui Hu Ting He Shuai Bai Keqin Chen Jialin Wang Yang Fan Kai Dang et\u00a0al. 2025. Qwen2. 5-omni technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.20215 (2025)."},{"key":"e_1_3_3_3_68_1","unstructured":"M Yinghao \u00d8 Anders R Anton S Bleiz MacSen\u00a0Del S Charalampos and D Chris. 2024. Foundation models for music: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.14340 (2024)."},{"key":"e_1_3_3_3_69_1","unstructured":"Ruibin Yuan Hanfeng Lin Shuyue Guo Ge Zhang Jiahao Pan Yongyi Zang Haohe Liu Yiming Liang Wenye Ma Xingjian Du et\u00a0al. 2025. Yue: Scaling open foundation models for long-form music generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2503.08638 (2025)."},{"key":"e_1_3_3_3_70_1","doi-asserted-by":"crossref","unstructured":"Ruibin Yuan Hanfeng Lin Yi Wang Zeyue Tian Shangda Wu Tianhao Shen Ge Zhang Yuhang Wu Cong Liu Ziya Zhou et\u00a0al. 2024. Chatmusician: Understanding and generating music intrinsically with llm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.16153 (2024).","DOI":"10.18653\/v1\/2024.findings-acl.373"},{"key":"e_1_3_3_3_71_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"}],"event":{"name":"SIGGRAPH Conference Papers '26: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers","location":"Los Angeles CA USA","acronym":"SIGGRAPH Conference Papers '26","sponsor":["SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers"],"original-title":[],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T18:19:32Z","timestamp":1784225972000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799902.3811191"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,19]]},"references-count":70,"alternative-id":["10.1145\/3799902.3811191","10.1145\/3799902"],"URL":"https:\/\/doi.org\/10.1145\/3799902.3811191","relation":{},"subject":[],"published":{"date-parts":[[2026,7,19]]},"assertion":[{"value":"2026-07-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}