Open-dLLM
Open diffusion language model for code generation, with pretraining, evaluation, inference, and checkpoints.
View stars on GitHubHey there! I’m Fred, a fourth-year Ph.D. student at Duke University. I have broad interests in machine learning and its applications in scientific problems. I work with Anru on statistical machine learning, Alex on generative models, Chris on ML4Bio. Previously, I worked with Pranam on protein design when he was at Duke. My research aims to scale up the math on GPUs and see what wonderful things emerge.
I have also interned at NVIDIA Research and ByteDance Seed.
I keep reminding myself this:
Long-term problems I’m pursuing:
Open-source projects I created to make science more accessible.
Open diffusion language model for code generation, with pretraining, evaluation, inference, and checkpoints.
View stars on GitHubA drop-in, efficient PyTorch implementation of protein language models.
View stars on GitHubTransparency and reproducibility are important to me. I ensure open code accompanying my first-author publications. Below are selected papers. Please refer to my Google Scholar for complete publications.



ICLR2026, Oral (top 1%)

DeLTa@ICLR2025 Outstanding Paper Award, and rejected by ICML, NIPS2025,ICLR2026


NIPS 2025, KDD 2025, ICLR 2025