Alex(ander) Gurung

I am a PhD student at the University of Edinburgh’s Institute for Language, Cognition and Communication, where I am supervised by Mirella Lapata and Nikolay Malkin. My research focuses on efficient reinforcement learning, long-form generation, and narrative reasoning. Recent work includes Lightweight Latent Reasoning for Narrative Tasks, presented at LIT @ ICLR 2026 in Rio, and Learning to Reason for Long-Form Story Generation, our COLM 2025 paper on next-chapter prediction and VR-CLI.

I previously completed my master’s in computer science at Georgia Tech’s School of Interactive Computing, and before that earned my BS in computer science with a minor in linguistics there as well.

I was also an AI resident at Meta AI, where I worked on commonsense reasoning for LIGHT. I have also worked on online radicalization with the SALT Lab under Diyi Yang in collaboration with David Muchlinski at Georgia Tech’s Sam Nunn School of International Affairs. Outside academia, I have worked as a machine learning engineer at TikTok and previously as a software engineer.

I’m always interested in talking about my research and learning more about what other people are doing, feel free to reach out!