Juntao Tan is a research scientist leading work on personalized LLMs and personalized agents. He has also collaborated on research involving Large Action Model data collection, multi-agent system design, on-device models, and on-device deployment of multi-modal models. Before joining the company in 2024, he earned a bachelor’s degree from Huazhong University of Science and Technology and a Ph.D. from Rutgers University.
In this blog, we’ll dive into the challenges of AI personalization, why current systems fall short, and how PersonaBench helps bridge the gap—paving the way for smarter, more reliable AI assistants.
We present TACO, a family of multi-modal large action models designed to improve performance on complex questions that require multiple capabilities and demand multi-step solutions.
