Biography

Rui Xu (徐锐) is a first-year Ph.D. student at Fudan University, jointly advised by Prof. Yinghui Xu and Prof. YuanQi at the AI³ Academy, while being jointly cultivated at Shanghai Chuangzhi Academy (SII). Previously, he received his Master’s degree from Fudan University in 2024 under the supervision of Prof. Yanghua Xiao at the Knowledge Work Lab. His interested research topics are mostly around autonomous generative agents, including (but are not limited to):

1. Role-Playing and Personalized Agents: Build Role-playing Language Agents ranging from virtual characters to real individuals, aligning long-context memory with corresponding roles, and accomplishing complex tasks from basic dialogue to behavioral decision-making.
2. Reasoning and Planning Language Models: Optimize the reasoning capabilities of current large language models from perspectives such as discretization, weak supervision, multi-agent systems, and short chain-of-thought, achieving better generalization in AI4S scenarios.
3. Long-Context Multimodal Large Language Models: Research fully multimodal large models capable of simultaneously processing mixed inputs of text, images, videos, audio, and more, developing alignment and fusion techniques to enable real-time multimodal interaction and long-term memory functions.