Yong Zheng-Xin
Current: Computer Science Ph.D. @ Brown University
Past: Research Scientist Intern @ Meta AI, Research Collaborator @ Cohere Labs

I am a fourth-year Ph.D. student in Computer Science at Brown University, advised by Prof. Stephen Bach. I am fortunate to have interned/collaborated with amazing researchers at Meta GenAI, FAIR, and Cohere Labs. My research goal is to create safe and intelligent systems to serve everyone in the world.
My most recent work is on reasoning models. Here are some recent findings:
- “quote-and-think” patterns enables English reasoning models to generalize to new languages without extra training (preprint).
I also actively work on safety alignment. I discovered that low-resource languages can jailbreak GPT-4 (⭑Best Paper Award, NeurIPS 2023 SoLaR Workshop; featured on New Scientist), which became the seminal work for multilingual red-teaming. My follow-up work uses mechanistic interpretability to study crosslingual generalization of alignment training that reduces toxicity (EMNLP 2024 Findings) and adversarial attacks (NAACL 2025 Findings).
My prior research is on generalization of multilingual LLMs. I co-developed Aya model (⭑Best Paper Award, ACL 2024) and worked on making speech models robust to accents (INTERSPEECH 2025). I investigated how pretrained LLMs can learn low-resource languages through language adaptation (ACL 2023) and synthetic data (EMNLP 2024 Findings). Besides, I also studied language-mixing behaviors (EMNLP 2023 CALCS, EMNLP 2023 Findings, ACL 2023 Findings) and contributed to Southeast Asian NLP as a Malaysian (SEACrowd, CVQA, AACL 2023 Tutorial).
Actively seeking industry and academic research opportunities.
Featured work/preprints (see all)
-
- EMNLP Findings, 2024
- ACL, 2024 (Best Paper Award)
- NeurIPS Workshop: Socially Responsible Language Modelling Research (SoLaR) , 2023 (Best Paper Award)
Miscellaneous
✈️ I lived in 6 different countries (USA, UK, S.Korea, Argentina, India, and Germany) for at least four months each when I studied at Minerva University.
🕺 I love dancing. I used to teach a bit of Lindy Hop and salsa. Also learned the full K-pop choreo of “Let’s kill this love” for my undergrad graduation.
👃 Used to work on lung cancer diagnosis research (Google Science Fair 2016 Finalist; work published on Journal of Thoracic Disease 2016 and featured on IEEE Spectrum) before pivoting to AI.