Guang-Lu Wan

Guanglu Wan is a Senior Technical Director at Meituan in Beijing, where he leads the Multimodal Large Language Model Team and oversees advancements in speech recognition, voice synthesis, and natural language dialogue systems. He holds a master's degree in computer science with a focus on speech recognition from Peking University and has over 17 years of experience in the field. Prior to Meituan, he served as a Principal Engineer at DiDi and held senior R&D engineering roles at Baidu, working on speech recognition and language understanding systems. He is known for research contributions including the LongCat-Flash-Omni omni-modal model, the MSR-86K multilingual speech corpus, and the CUSIDE framework for streaming ASR.