Abstract: Hands are essential tools for humans to act, interact, and communicate in nearly all daily activities, highlighting the critical need for precise modeling to achieve highly realistic virtual avatars. However, the complexity of hands, characterized by their scale, degrees of freedom, and versatility, poses significant challenges for current human-centered AI frameworks. These limitations are evident across various domains, including human motion models, generative image and video models, and 3D human reconstruction. In this talk, I will discuss the key challenges in 3D hand modeling and reconstruction and share our efforts to develop large-scale hand models to address these obstacles. I will also present our approach to real-time hand detection and our ongoing advancements in reconstructing 3D hands in real-world coordinates.