Yongbin Li
Head of Dialog Intelligence & Code Intelligence, Alibaba Tongyi Labs
Yongbin Li graduated from Tsinghua University and is currently the head of the Dialogue Intelligence and Code Intelligence at Alibaba’s Tongyi Lab. His research focuses on large model technologies, such as Post-Training, Character Model, Code Model, and Agents. He is also responsible for the large model technologies of several products, including Tongyi Xingchen (character dialogue, emotional companionship, and digital humans), Tongyi Lingma (coding assistant and AI programmer), Tongyi Xiaomi (intelligent customer service), and Tongyi Tingwu (audio and video assistant). Since 2020, he has published over 90 papers in top international conferences (such as ICLR, NeurIPS, ICML, ACL, EMNLP, and CVPR) in the fields of pre-training, multimodality, dialogue/code, and large models. He has also served as an area chair for top international conferences such as ACL, NAACL, and WSDM.
Topic
QwenStar Character Model - Explore modeling a “person”!
By modeling the world's knowledge, the Big Language Model demonstrates powerful information processing, understanding and reasoning capabilities. The Character Model goes one step further, aiming to explore the complex entity of “human being” in depth, and attempts to portray human knowledge, emotion, personality, memory, morality and mental activities in multiple dimensions. Based on the Character Model, a variety of applications can be developed, including role-playing, real-life replicas, emotional accompaniment, and digital people, which can be widely used in various scenarios, such as social networking, gaming, and consumer electronics, to provide users with a more personalized and immersive interactive experience. QwenStar is committed to in-depth research and innovative exploration of character models, with the goal of building “interesting and useful” multilingual and multimodal Humanoid Agents. This presentation will systematically introduce QwenStar's latest progress in the field of Character Model, including the overall architecture, core technology, application cases and future development direction.
