I am a machine learning research scientist at Apple AIML đ. I earned my PhD in the Machine Learning Program at Georgia Tech, working in the Neural Data Science Lab led by Prof. Eva L. Dyer. Over the past few years, I interned at Apple AIML, Cajal Neuroscience, and Meta. Previously, I got my Bachelorâs degree from Fudan University majoring in physics working on Quantum Hall effect and Superconductors.
My ultimate research goal is to create a next-generation deep learning framework that incorporates logic. I believe that the critical path toward achieving this involves developing large-scale learning methods that are both more generalizable and explainable. To this end, I have been focusing on the following topics:
- Large-scale Pretraining and Alignment for Time Series and Beyond: Bias in large models (ICMLâ24), Group-Aware Embeddings for transformers (ICLRâ24), Frequency-Aware MAE (ICLRâ24 TS4H), Foundation model for neurons (NeurIPSâ22), Content-Style separation for time-series (NeurIPSâ21).
- Representation Learning, Contrastive Methods, and Data Augmentation: Alignment theory for contrastive learning (coming soon), Sample-aware augmentation (WACVâ24), Upsampling augmentation for graphs (ICMLâ23), Cross-sample augmentation in SSL (NeurIPSâ21 SSLTP).
- Generative Modeling and Segmentation of Medical Images: Open-source dataset for multiscale brain modeling (NeurIPSâ22 DnB), Multiscale brain modeling (ICIPâ21), Population-level variability in brain (MICCAIâ20).
Outside of research, I am a fan of indoor climbing, fine dining, and playing with my two lovely catsđ±.
I am also somewhat of a hunter.
Contact Me
- My email address is rliu361{at}gatech{dot}edu.
- My full CV is here. (Updated Feb, 2024)