Directed Reading Program (DiRP) on trustworthy large language models.
Instead of isolated properties, we target on a holistic trustworthiness covering every properties in one solution.
On the need of data privacy and more data, we strive to join the knowledge from a fair amount of users to train powerful deep neural networks without sharing data.
On the concern of data privacy, we aim to develop algorithms towards learning accurate models privately from data.
We aim to early detect and intervene dementia diseases leveraging the power of (Generative) AI.
Supervised learning on subspace data which could model real data like skeleton motion.