Welcome! I’m Zitong (Cynthia) Huang, a 4th-year undergraduate student at the University of Southern California, majoring in Computer Engineering & Computer Science. I have been fortunate to work closely with Prof. Ajitesh Srivastava and Prof. Robin Jia . I am also glad to be a member of USC CAIS++ , where I explore how AI can be applied for social good and collaborate on projects at the intersection of technology and impact.
Broadly, I aim to develop methods that make foundation models more efficient, reliable, and generalizable across resource-constrained settings. My research interests include:
-
Automated Machine Learning: How can we automatically make principled decisions about model architectures, discovering the most sparse, compact, and high-performing structures within a vast design space?
Specific topics include: Neural Architecture Search (NAS), model compression, sparse & compact networks. -
Efficient Adaptation: How can we enable fine-grained, low-overhead behavioral steering for foundation models after pre-training, allowing them to adapt to new tasks, users, or constraints with minimal compute?
Specific topics include: model steering, lightweight post-training, LoRA-based adaptation.
If you’re interested in my work, feel free to reach out!
📰 Recent News
- Oct 2025 — Selected as an Ming Hsieh Institute Undergraduate Scholar at USC!
- Oct 2025 — Our work “SWAT-NN: Simultaneous Weights and Architecture Training for Neural Networks in a Latent Space” was accepted to IEEE BigData 2025!
- Oct 2024 — Our work “Simultaneous Weight and Architecture Optimization for Neural Networks" was accepted to NeurIPS 2024 FITML Workshop!
- April 2024 — Selected as a USC Women in Science and Engineering(WiSE) Undergraduate Research Scholar!
📚 Publications
-
SWAT-NN: Simultaneous Weights and Architecture Training for Neural Networks in a Latent Space .
Zitong Huang, Mansooreh Montazerin, Ajitesh Srivastava. IEEE International Conference on Big Data 2025. -
Simultaneous Weight and Architecture Optimization for Neural Networks .
Zitong Huang, Mansooreh Montazerin, Ajitesh Srivastava. NeurIPS 2024 FITML (Fine-Tuning in Modern Machine Learning) Workshop.
🎓 Teaching & Service
- Course Producer — EE 155 (Introduction to Computer Programming for Electrical Engineers)
USC Viterbi School of Engineering
Aug 2023 – Dec 2023
Supported undergraduate students through weekly labs, office hours, and debugging guidance.
Helped redesign instructional materials to improve conceptual clarity and assignment structure.