Joseph Marvin Imperial

This is an outdated website. Please go to https://www.josephimperial.com/

Kumusta! I'm Joseph, a PhD Candidate at the UKRI CDT for Accountable, Responsible, and Transparent AI (also called ART-AI) at the University of Bath. I'm also a Pivotal Research Fellow at the London Initiative for Safe AI (LISA).

I do state-of-the-art research in AI and NLP. I'm particularly interested in the following research directions:

• Aligning, Controlling, and Standardizing for/with Generative AI
  (Arxiv 2025, EMNLP 2024, EMNLP 2023, GEM 2023).

• Benchmarking Safety, Alignment, Capabilities, and Risks of AI
  (Global PIQA, ICML 2024, AILuminate 1.0, Humanity's Last Exam).

• Building Multilingual Low-Resource Language Corpora
  (ICLR 2025, EMNLP 2025, ACL 2025, EMNLP 2024, EMNLP 2023, NAACL 2024).

I'm originally from the Philippines but am currently based in the UK for the rest of my Ph.D. studies. I'm also affiliated with the Department of Computer Science as an NLP researcher of the Human Language Technology (HLT) Lab at National University, Philippines.

You may visit my  Google Scholar page for the complete list of my previous research engagements.