Qwen2-Audio Technical Report

Nan Duan is head of foundation model post-training at Qwen and a vice president at Alibaba Group. His public profile highlights work on foundation models and natural language processing, after earlier research leadership at Microsoft Research.

Chao Zhang is an applied scientist in the Alibaba Foundation Model team. His public profile notes a PhD in computer science from the University of Illinois Urbana-Champaign and research interests in NLP, large language models, reasoning, and multimodal generation.

Zhengyuan Liu is a research scientist at Alibaba Group and a PhD student at the National University of Singapore. His public profile highlights work in natural language processing, vision-language models, and grounding.

Zhen Ye is a researcher in the Qwen team at Alibaba Cloud. His public profile notes a PhD in computer science from the University of Massachusetts Amherst and research interests in natural language understanding, generation, and reasoning.

Research scientist at Alibaba working on speech processing, multimodal learning, natural language processing, and efficient human-computer interaction.

Jiaqi Wang works on machine learning, multimodal large language models, and AI for healthcare. Public profiles connect him to the Qwen2-Audio technical report.

Shen Gao is a PhD student at Zhejiang University working on multimedia and large language models. His public profiles connect him to Qwen2-Audio and related multimodal systems including OmniParser.

Weiqiang Wang is a PhD student working on multimedia and multimodal AI. Public profiles connect him to the Qwen2-Audio technical report and related research.

Principal scientist at Moonshot AI working on multimodal large models.

Yeyun Gong is a researcher and engineering leader focused on multimodal large language models, grounding, and large-scale knowledge systems. His homepage lists selected work including Qwen2-Audio.

OpenAI contributor credited on the GPT-4 Technical Report; previously a Dropbox engineer and a Ph.D. student at UC Berkeley focused on machine learning and robotics.

Associate professor at the University of Virginia and Qwen contributor whose research focuses on personalization and recommender systems, online advertising, and AI systems.

Xian-Sheng Hua is a computer vision and multimodal AI researcher known for work in visual recognition, multimedia understanding, and large AI systems. Public profiles tie him to Alibaba DAMO Academy and related academic service roles.

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.

Xiaoyong Du works on multimodal large language models and language agents, with public profile text highlighting omni models, visual agents, and GUI agents. His homepage explicitly identifies him with Qwen.

Alibaba researcher working on large language models and multimodal pretraining; public research profiles connect An Yang to Qwen-related work and earlier study at Peking University.

Yuanzhi Zhu is a Qwen researcher whose public work includes multimodal and audio-language models.

Senior research scientist in Tongyi Lab whose official profile highlights post-training, AI for science, evaluation and alignment, multimodal reasoning, and large language model reasoning.

Research intern at Alibaba Group focused on multimodal understanding and generation, large multimodal models, and reinforcement learning; coauthor of Qwen2-Audio.

Second-year PhD student at Peking University focused on audio-language foundation models, trustworthy AI, and embodied AI; coauthor of Qwen2-Audio.

Research scientist in Tongyi Lab and technical lead of Qwen2-Audio, with public work on audio-language models.

Machine learning engineer and researcher interested in large language models and multimodal audio-language systems; coauthor of Qwen2-Audio.

Research scientist in Tongyi Lab whose public profile highlights work on speech processing, machine learning, and multimodal large language models.

Yushi Hu is a senior research engineer at Shanghai AI Laboratory and a founding member of OpenMMLab. Public arXiv records also list him as a coauthor of Qwen2-Audio.