I'm a Master’s student in the Master of Language Technologies (MLT) program at Carnegie Mellon University. I come from an applied machine learning background, and my current interests focus on multimodal learning, spoken language modeling, and the intersection of language, audio, and vision.
I am particularly interested in how modern foundation models enable more natural human–computer interaction, as well as how multimodal systems can reason over heterogeneous signals. Outside of coursework and research, I enjoy experimenting with new tools, frameworks, and model architectures.
- Blogger 📖 | I occasionally write about machine learning, systems, and topics I find interesting.
- Experimentalist 🚀 | I build and share small experimental projects when time permits.
- Mint Tea Connoisseur 🍵 | Still convinced good mint tea is an underrated skill.