Supervised multiple PhD students who successfully defended dissertations and joined prestigious institutions such as NVIDIA, Microsoft, Princeton University, Texas A&M University, and Northwestern University
Student dissertation topics include: robust reward modeling for LLM alignment, efficiency and steerability of self-attention mechanisms, training/inference/sample efficiency of language models, and parameter efficiency of neural language models
Collaborated with Microsoft Azure AI to release work on parameter-efficient fine-tuning on Hugging Face
Led the release of new Phi model family additions: SlimMOE Framework and open-source models Phi-mini-MoE-instruct and Phi-Tiny-MoE-instruct
Published preprint: 'IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining'
Research Experience
Associate Professor at Georgia Tech conducting research in machine learning and LLMs
Collaborates with Microsoft and Amazon on research projects
Collaborates with Prof. Hua Wang at ETH Zurich to recruit PhD students for research at the intersection of modern circuit design and machine learning
Collaborates with Prof. Yongsheng Chen in the School of Civil and Environmental Engineering at Georgia Tech to recruit PhD students for research at the interface of computational chemistry and machine learning
Co-organized Georgia Statistics Day 2023 with Prof. Shihao Yang