Alan Liang

I'm a Computer Science master's student at USC and a machine-learning researcher at the USC Information Sciences Institute, where I build structure-aware models of protein interaction, predict TCR–pMHC binding, and analyze immunology data for cancer-vaccine research.

I also study how language models fail. That work spans unlearning and safety in LLMs, and dialect bias in toxicity detection.

View CV

News

Sep 2026: Submitted PIT-GCL to ICLR 2027.
Nov 2025: Joined AI4Health at USC ISI, advised by Ruishan Liu.
Sep 2025: Presented at FedCSIS 2025.
Jul 2025: Placed 7th overall in the FedCSIS 2025 Chess Puzzle Difficulty Prediction Challenge. Results published in IEEE.

Education

University of Southern California

Aug 2025 – May 2027 (Expected)

M.S. in Computer Science · Los Angeles, CA

University of California, Riverside

Sep 2021 – Mar 2025

B.S. in Computer Science · Riverside, CA

Research interests

Biomedical machine learning · Protein interaction modeling · TCR–pMHC recognition · Representation learning · Natural language processing · Adversarial training · Immunology data science · Cancer vaccine design

Skills

Languages: Python, Java, Scala, C++, JavaScript, TypeScript, SQL
Libraries: PyTorch, PyTorch Geometric, XGBoost, AlphaFold, Biopython, SciPy, Transformers (Hugging Face), scikit-learn, pandas, NumPy, TensorFlow, Matplotlib
Tools & Platforms: Git, Docker, GCP, AWS, Hadoop, Spark, Azure