I am currently a Research Engineer at Kuaishou Technology. I received my Ph.D. in Fluid Mechanics from Peking University in 2020, advised by Prof. Yue Yang, and my B.S. in Mechanics and Economics from Peking University in 2015.

Since joining Kuaishou in 2020, my work has focused on three directions: (1) agentic coding large language models (LLMs), (2) AIGC generative video processing large models, and (3) server-side pre-processing and on-device post-processing AI algorithms. My current research focuses on LLMs, particularly agentic coding. Previously, I worked on image/video restoration and image/video generation. I have published 10+ papers at top-tier venues including CVPR, ICML, ECCV, and AAAI.

自 2020 年加入快手以来，工作聚焦于三个方向：（1）Agentic Coding 大语言模型：主导 KAT-Coder-Pro V2 模型后训练，在 Artificial Analysis Coding Index 中位列全球第六、国产第一；（2）AIGC 生成式视频处理大模型：主导研发并上线基于扩散模型的生成式视频处理大模型，在兼顾保真度的同时，显著提升视频清晰度与纹理细节丰富度，取得显著用户时长增长收益；（3）服务端前处理与移动端后处理 AI 算法：研发上线服务端视频增强修复算法，覆盖去压缩、去模糊、超分等方向；研发上线移动端 NPU/GPU 后处理算法在画质与功耗之间取得有效平衡。