About

I’m a fourth-year Ph.D. student in Machine Learning at the Georgia Institute of Technology, co-advised by Dr. Bo Dai and Dr. Chao Zhang. I also work closely with Dr. Nan Du at Apple.

My research focuses on large-scale multi-modal foundation models, with a core emphasis on developing scalable, adaptive, and highly personalized generative systems. In particular, I work on:

• Scaling multi-modal generative models — efficient adaptive computation for diffusion transformers (EC-DIT), amortized contrastive language-image pretraining (AmorLIP), and unified multi-modal diffusion.
• LLM adaptation and personalization — lightweight adapters for black-box LLMs (BBox-Adapter), model factorization for user-level personalization (Hydra).
• Agentic planning with LLMs — closed-loop planning with environmental feedback (AdaPlanner), tool-using QA (ToolQA).

Before Georgia Tech, I received a dual engineer’s degree from CentraleSupélec (Paris) and a combined B.S./M.S. from Xi’an Jiaotong University through the Honors Youth Program.

I have had the privilege of interning at Apple’s Foundation Model Team (summers 2024 and 2025).

If you’d like to chat about research, collaborations, or just good coffee in Atlanta or Cupertino, feel free to reach out at haotian.sun@gatech.edu.