Siyin Wang
Siyin Wang is a PhD student at Fudan University advised by Professor Xipeng Qiu, affiliated with the Fudan NLP Lab and the Shanghai Innovation Institute. Her research focuses on language intelligence, large language model alignment, multimodality, and embodied AI. She is known for her work on Vision-Language-Action models and In-Context World Modeling, a framework that enables robot policies to adapt to novel configurations by inferring system variables from self-generated interactions without parameter updates.
“ICWM enables robot policies to autonomously infer essential system variables from a short history of self-generated, task-agnostic interactions.”
Source→“ICWM treats it as a system identification problem solved through in-context learning”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.