{"author":{"name":"Zeyue Tian, Binxin Yang, Zhaoyang Liu, Jiexuan Zhang, Ruibin Yuan, Hubery Yin, Qifeng Chen, Chen Li, Jing Lyu, Wei Xue, Yike Guo","slug":"zeyue-tian-binxin-yang-zhaoyang-liu-jiexuan-zhang-ruibin-yuan-hubery-yin-qifeng-chen-chen-li-jing-lyu-wei-xue-yike-guo","article_count":1,"latest_published_at":"2026-04-28T14:39:53.087+00:00","profile_url":"https://vff.ai/authors/zeyue-tian-binxin-yang-zhaoyang-liu-jiexuan-zhang-ruibin-yuan-hubery-yin-qifeng-chen-chen-li-jing-lyu-wei-xue-yike-guo","api_url":"https://vff.ai/api/authors/zeyue-tian-binxin-yang-zhaoyang-liu-jiexuan-zhang-ruibin-yuan-hubery-yin-qifeng-chen-chen-li-jing-lyu-wei-xue-yike-guo"},"articles":[{"slug":"audio-omni-extending-multi-modal-understanding-to-versatile-audio-generation-and","title":"Audio-Omni Unifies Generation and Editing Across Sound, Music, Speech","url":"https://vff.ai/article/2026/04/28/audio-omni-extending-multi-modal-understanding-to-versatile-audio-generation-and","content_type":"research_summary","summary":"Researchers have introduced Audio-Omni, a unified framework that combines audio understanding, generation, and editing across sound, music, and speech in a single model. The system pairs a frozen multimodal large language model for reasoning with a trainable Diffusion Transformer for synthesis. To address the scarcity of audio editing training data, the team created AudioEdit, a dataset of over one million curated editing pairs. The framework achieves state-of-the-art results on multiple benchmarks and demonstrates emergent capabilities including knowledge-augmented reasoning, in-context generation, and zero-shot cross-lingual control.","published_at":"2026-04-28T14:39:53.087+00:00","updated_at":"2026-05-07T02:19:52.375108+00:00","source":{"url":"https://arxiv.org/abs/2604.10708","name":"ArXiv (cs.AI)"},"featured_image":null,"categories":[{"name":"Research","slug":"research"},{"name":"Multimodal","slug":"multimodal"},{"name":"Voice & Video AI","slug":"voice-video-ai"},{"name":"Generative AI","slug":"generative-ai"}]}]}