Algorithm Researcher · UniDT
Algorithm research for large language model training.
I am an Algorithm Researcher at UniDT. My work covers pretraining, supervised fine-tuning, reinforcement learning, and evaluation, with additional research in robustness, uncertainty, privacy, and applied statistics.
SELECTED WORK
Publications & Projects
Learning History-Aware Paraphrase Robustness in LLMs under Epistemic Uncertainty
Private Minimum Hellinger Distance Estimation
Sharp Large Deviations and Gibbs Conditioning for Threshold Models
LLM Agent for Crash Analytics and Adaptive Feature Enrichment
Neyman Pearson Classification for Heart Transplant Rejection
BLOGS
Latest Blogs
GRPO: Learning from a Group of Answers
How group rewards drive policy updates, with clipping, DAPO, GSPO, and practical reward design.
Read PDF
FiLM: A Simple Way to Let One Input Guide Another
An intuitive introduction to feature-wise conditioning, neural-network integration, and training.
Read PDFEXPERIENCE
Current and previous roles
Algorithm ResearcherUniDT · Current
Postdoctoral Research FellowGeorge Mason University
EDUCATION
Academic background
PhD in Statistical ScienceGeorge Mason University · 2025
MS in StatisticsRutgers University · 2019
BS in MathematicsShandong University · 2017