M.S. Computer Science · USC

Alan Liang

I'm a Computer Science master's student at USC and a machine-learning researcher at the USC Information Sciences Institute. There 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 Read the research

I'm applying to PhD programs for Fall 2027 admission.

News

May 2026: Submitted PIT-GCL to NeurIPS 2026.
Nov 2025: Joined AI4Health at USC ISI, advised by Ruishan Liu.
Sep 2025: Presented at FedCSIS 2025.

Selected publications

All publications

A Stacking-Based Ensemble Approach for Predicting Chess Puzzle Difficulty Published

Alan Liang, Cenzhi Liu, Kai Wang, Ethan Liu

FedCSIS 2025 · published in IEEE

DOI Google Scholar

BibTeX

@inproceedings{liang2025stacking,
  author    = {Liang, Alan and Liu, Cenzhi and Wang, Kai and Liu, Ethan},
  title     = {A Stacking-Based Ensemble Approach for Predicting Chess Puzzle Difficulty},
  booktitle = {Proceedings of the 20th Conference on Computer Science and Intelligence Systems (FedCSIS)},
  series    = {Annals of Computer Science and Information Systems},
  volume    = {43},
  pages     = {819--824},
  year      = {2025},
  publisher = {Polish Information Processing Society},
  doi       = {10.15439/2025F1698},
  issn      = {2300-5963}
}

PIT-GCL: Protein Interaction using Topological Graph Contrastive Learning Under review

Jae Won Choi, Ryoonki Hong, Alan Liang, Manjula Adiveppa Wader, Bingsong Zeng, Peiyang Tang, Longwei Liu, Ruishan Liu

Submitted to NeurIPS 2026

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

Relevant coursework: Artificial Intelligence, Machine Learning, Natural Language Processing, Algorithm Engineering, Database Management, Data Structures & Algorithms, Compiler Design, Operating Systems.

Awards

2025: Placed 7th overall in the FedCSIS 2025 Chess Puzzle Difficulty Prediction Challenge. Results published in IEEE.

Research interests

Biomedical machine learningProtein interaction modelingTCR–pMHC recognitionRepresentation learningNatural language processingAdversarial trainingImmunology data scienceCancer vaccine design

Skills

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