Qwen2.5-Omni Technical Report

Yale Song is an assistant professor in artificial intelligence at Yonsei University and is also affiliated with the Stanford AI Lab while working part-time with Adobe Research.

Researcher whose public homepage focuses on computer vision, multimodal foundation models, and embodied AI; publication context connects Shilong Liu to the Qwen2.5-Omni technical report.

Jianwei Niu is a tenure-track research assistant professor in the School of Data Science at Lingnan University, Hong Kong. His research focuses on multimodal learning, computer vision, and embodied AI.

Alibaba senior technology leader and researcher associated with Qwen. Public profiles list him with Alibaba Group, and official Alibaba Cloud coverage identifies him as a chief technology officer leading large-model work.

Research scientist at Qwen, Alibaba, whose public OpenReview profile lists work on vision-language models and large language models.

Linjie Li is a research scientist at Alibaba Group and a contributor to the Qwen2.5-Omni Technical Report.

Research engineer at Alibaba Group working on audio and multimodal foundation models, multimodal RL, and speech processing; coauthor of Qwen2.5-Omni.

Research scientist and GPT-4 coauthor known for work on generative modeling, diffusion methods, and machine learning systems.

Jianfei Chen is an assistant professor at Monash University. His research spans computer vision, machine learning, multimodality, and trustworthy AI.

Research scientist in Tongyi Lab and technical lead of Qwen2.5-Omni, with public work on end-to-end speech understanding and generation.