Weiliang Zhao

I'm a first-year PhD student at Columbia University, advised by Professor Junfeng Yang and Professor Zhou Yu. My research interests mainly include Alignment of LLMs, Continual Learning and Mechanistic Interpretability.

I hold a BSc in Mathematics from the University of Edinburgh, where I was advised by Prof. Burak Buke.

📮Email  /  🔗LinkedIn  /  🎓Google Scholar  /  📃CV

A proactive defense framework that injects strategically crafted spurious outputs to mislead attackers’ optimization loops, prematurely collapsing multi-turn jailbreak searches and dramatically reducing LLM vulnerability.

Vision-language models often answer image questions correctly without ever looking at the image. A contrastive probing framework shows this "mirage" behavior is linearly decodable from internal activations, separating genuine visual grounding from language-prior shortcuts.

A Generalised jailbreaking technique by encouraging higher levels of diversification and adjacent obfuscated prompting to evaluate the vulnerabilities of LLMs.

We propose a method designed to enhance the detection of LLM-generated text by learning to rewrite more on LLM-generated inputs and less on human generated inputs.

Center for AI Safety, San Francisco, CA — Research Scientist Intern
May – August 2026

I would like to acknowledge the Thinker Research Grants support from Thinking Machine.

Beyond research, I love traveling and scuba diving 🤿 — here are my footprints around the world 🌍.

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.