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 worked with researchers at Meta GenAI (with Jianfeng Chi), Meta AI FAIR (with Jean Maillard and Michael Auli), and Cohere Labs (with Julia Kreutzer, Beyza Ermis, Marzieh Fadaee, and Sara Hooker).
My research goal is to create safe intelligent systems that can serve everyone, and I currently work on reasoning and alignment. My recent work/findings include:
- test-time scaling of reasoning models generalizes well to new languages but not new domains (preprint).
- more coming soon :)
My past research focuses on building safe and capable multilingual LLMs. Some of my notable work includes co-developing Aya model (⭑Best Paper Award, ACL 2024) and discovering that low-resource languages can jailbreak GPT-4 (⭑Best Paper Award, NeurIPS 2023 Socially Responsible Language Modeling Workshop). This work became the seminal work for multilingual red-teaming, and it was featured on New Scientist as well as the first International Scientific Report on the Safety of Advanced AI (2024).
featured work (see all)
-
- ACL, 2024 (Best Paper Award)
- NeurIPS Workshop: Socially Responsible Language Modelling Research (SoLaR) , 2023 (Best Paper Award)
news
05 / 2025 | Gave an invited talk at MilaNLP lab. |
---|---|
05 / 2025 | 1 paper accepted! Work on mitigating accent bias in ASR was accepted to INTERSPEECH’25. Work was done during Meta internship. |
02 / 2025 | 1 paper accepted! Work on cross-lingual finetuning attacks was accepted to NAACL’25 findings. Work was done during Meta internship. |
09 / 2024 | 4 papers accepted! LexC-Gen, SEACrowd, and crosslingual alignment were accepted to EMNLP. CVQA was accepted to NeurIPS. |
08 / 2024 | Aya Model paper received the ⭑Best Paper Award at ACL 2024. |
07 / 2024 | Gave an invited talk at London Data Week. |
06 / 2024 | Started research scientist internship at Meta AI (FAIR)! |
05 / 2024 | 1 paper accepted! A Safe Harbor for AI Evaluation and Red Teaming is accepted to ICML. |
02 / 2024 | Released Aya model and dataset papers! I also presented Aya multilingual safety research at Aya Grand Finale. |
11 / 2023 | Co-organized the tutorial on current status of NLP in South East Asia at AACL 2023. |
10 / 2023 | “Low-Resource Languages Jailbreak GPT-4” received the ⭑Best Paper Award at NeurIPS 2023 Socially Responsible Language Modeling (SoLaR) workshop. |
09 / 2023 | Joined the Cohere For AI’s Responsible Deployment Team for Aya red-teaming. |
08 / 2023 | Served as the Area Chair (Multilingualism & Linguistic Diversity Track in EMNLP 2023). |
05 / 2023 | Media: Our code-switching paper was featured by Wired. |
05 / 2023 | 3 papers accepted! BLOOM+1, BLOOMZ and code-switching survey were accepted to ACL 2023. |
03 / 2022 | 2 papers accepted! T0 was accepted to ICLR (Spotlight). PromptSource was accepted to ACL Demo. |
06 / 2021 | Started PhD at Brown University. |
miscellaneous
-
I am a Malaysian 🇲🇾 and I contributed substantially to NLP for South-East Asian (SEA) languages. For instance, I studied language-mixing behaviors for SEA languages (EMNLP 2023 CALCS, EMNLP 2023 Findings, ACL 2023 Findings), contributed Malaysian cultural data to SEACrowd and CVQA, and co-hosted a tutorial for SEA NLP (AACL 2023).
-
I went to Minerva University during my undergrad so I had the opportunity to travel and live in six different countries for at least four months: United States (San Francisco), South Korea (Seoul), India (Hyderabad), Germany (Berlin), Argentina (Buenos Aires), and United Kingdom (London).
-
One of my biggest passion outside of work is dancing 🕺, especially salsa and bachata. I also dance a bit of Lindy Hop, Argentine Tango and K-pop. I usually check out the dance scenes in the city when I travel to conferences ––– if you also enjoy dancing, hmu we can check them out together.