Adithya Venkatadri Hulagadri is a PhD student in the Department of Informatics Department, King’s College London and is aligned to the Centre for Doctoral Training in Safe and Trusted AI (STAI).

His research aims to study the nature of deception in artificial agents using the frameworks of emergent communication and theory of mind, which explores how one agent can account for others’ beliefs. This work could help identify incentives that may lead artificial agents to act against human interests, as well as support the development of transparency mechanisms.

Prior to pursuing his PhD, Adithya worked as an AI Engineer at AI Singapore, working on evaluations of Large Language Models (LLMs) for Southeast Asian languages. He also formerly worked as a Data Scientist at Indeed.com, helping to match job seekers to open roles.

He obtained a master’s degree with distinction in cognitive science from the University of Edinburgh in 2024, and dual bachelor’s degrees in computer science and business from Nanyang Technological University in Singapore, both with first class honours.

Beyond academia, Adithya is a keen Sanskrit enthusiast, with a particular interest in its links to other Indo-European languages including Latin, Greek and Persian, as well as to Southeast Asia through Buddhist and Hindu traditions.

Thesis title and abstract: The Evolution of Deception Through Emergent Communication

Research Interests

• Theory of Mind
• Natural Language Processing
• Reinforcement Learning
• Computational Linguistics

PhD Supervisory Team

• Primary Supervisor - Dr. Gerard Canal
• Second Supervisor - Dr. Stefan Sarkadi
• Third Supervisor - Prof. Peter McBurney

More Information

• Publications
• Personal Profile