About Me 关于我
I am currently conducting MLLM research at Xiaohongshu. I received my B.S. in Physics from the University of Chinese Academy of Sciences, and obtained my Ph.D. in Signal and Information Processing under the supervision of Prof. Jun Yang and Prof. Feiran Yang. My research and work focus on Generative Models and their applications in Audio Signal Processing.
我目前在小红书进行多模态大模型研究。我在中国科学院大学物理系获得学士学位，并在杨军以及杨飞然老师的指导下获得信号与信息处理博士学位。我的研究和工作主要关注生成模型及其在音频信号处理中的应用。
Work Experience 工作经历
-
MLLM Researcher 多模态大模型算法研究员 2026.03 - Present 2026.03 - 至今Multimodal large language model research, with focus on speech generation, synthesis, and multi-task understanding. 多模态大模型研究，涵盖语音生成、合成与多任务理解。
-
Senior Researcher 应用研究 2024.07 - 2026.03 2024.07 - 2026.03Audio front-end processing for RTC, speech understanding (speech separation, speaker diarization), and speech generation (text to speech). 面向RTC的音频前处理、语音理解（语音分离、说话人日志）以及生成（语音合成）。
Education 教育经历
-
University of Chinese Academy of Sciences 中国科学院大学 2019.09 - 2024.07 2019.09 - 2024.07Ph.D. in Signal and Information Processing 信号与信息处理博士
-
University of California, Berkeley University of California, Berkeley 2018.07 - 2018.12Exchange Student 物理系交换生
-
University of Chinese Academy of Sciences 中国科学院大学 2015.09 - 2019.07B.S. in Physics 物理学学士