I'm a Computer Science PhD student at the University of Auckland, working on multimodal AI and world models.

I’m especially curious about a simple question: how can we build AI systems that understand what they see, know where their answers come from, and are a little less likely to confidently make things up?

• 🧠 Multimodal reasoning and knowledge integration
• 🔍 Hallucination detection and mitigation
• 🌏 Reliable, responsible, and culturally aware AI
• 🩺 AI for health and other socially important applications

I enjoy working across computer science, healthcare, and social science, turning research ideas into practical experiments with Python and PyTorch. My recent work includes CABIN, on reducing bias in vision-language models, and LIBRA, on measuring language-model bias in local contexts.

Based in Auckland, New Zealand 🇳🇿