Liangdong Wang

In 2022, he joined the Beijing Academy of Artificial Intelligence (BAAI), focusing on the training and algorithm optimization of large language models (LLMs). He was mainly responsible for algorithmic work during the pretraining and post-pretraining stages. During this period, he led and participated in the design and development of BAAI's in-house LLM, the Aquila series, and played a key role in the continuous open-sourcing of the Aquila models. Additionally, he was a major contributor to several open-source projects at BAAI, including FlagAI and FlagScale.