Speech and Audio Models

Research scientist at Tongyi Lab, Alibaba Group, working on multimodal large language models, machine reasoning, and efficient learning.

Junyang Lin (Justin Lin) is a researcher and open-source maintainer known for the Qwen family of models. His public profiles list interests in LLMs, AI agents, multimodal learning, long-horizon reasoning, world models, and reinforcement learning; multiple March 2026 news reports said he stepped down from the Qwen tech lead role.

Jin Xu's homepage says he leads the audio group at Qwen Team, Alibaba, working on audio understanding, real-time multimodal interaction, speech synthesis, general audio synthesis, and audio-centered chat models. He previously completed a Ph.D. at IIIS, Tsinghua University and received a BSc in 2018 from Beijing University of Posts and Telecommunications.

Jingren Zhou is Chief Technology Officer of Alibaba Cloud. Public speaker biographies describe him as a computer scientist and entrepreneur whose work includes large-scale AI and cloud systems.

Researcher at Kyutai and coauthor of the Moshi: a speech-text foundation model for real-time dialogue.

Qwen researcher whose work spans language model alignment, multilingual models, and large-scale reasoning.

Research scientist in Tongyi Lab whose official profile highlights multimodal large language models, efficient training, and post-training.

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

Xinyu Zhang

Junyang Lin

Jin Xu

Jingren Zhou

Manu Orsini

Baosong Yang

Pei Zhang

Yongqi Wang