ADM+S researcher secures UNSW Spinout Fellowship to advance GenAISim platform
Author ADM+S Centre
Date 4 May 2026
A researcher from the ARC Centre of Excellence for Automated Decision-Making and Society has been awarded a competitive commercialisation fellowship to further develop a generative AI simulation platform that can be used by decision makers.
Dr Yunchen (Devin) Hua from UNSW has been selected for the UNSW Founders Engineering Spinout Fellowship, a 12-month program designed to support early-career researchers in translating their work into valuable solutions that benefit humanity.
The fellowship will support Dr Hua’s work on a tool designed to help decision-makers better understand and simulate the impacts of AI systems as part of the GenAISim: Simulation in the Loop for Multi-Stakeholder Interactions with Generative Agents project at ADM+S.
“It is truly through the collective efforts and collaboration of all the universities and research institutions involved that this project was established, which has given me the opportunity to pursue this line of research and ultimately led to this opportunity,” said Dr Hua.
The tool SOCIA (Simulation Orchestration for Computational Intelligence with Agents) acts as a bridge between policy questions and executable simulations, enabling users to model “what-if” scenarios and assess the potential impacts of interventions.
SOCIA addresses a key challenge in policy and planning: building simulations that are not only technically functional but also robust, transparent, and grounded in real-world evidence. It semi-automatically translates social and urban policy requirements into simulation code, supported by human-in-the-loop refinement.
A co-authored paper on this research titled SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization (Devin Yuncheng Hua, Sion Weatherhead, Mehdi Jafari, Hao Xue, Flora D. Salim) has been accepted for presentation at the 64th Annual Meeting of the Association for Computational Linguistics, a leading international conference in computational linguistics and natural language processing in July. The event brings together global experts to present cutting-edge research in AI language technologies and their real-world applications.
Flora Salim, Chief Investigator at ADM+S, said the fellowship represents a valuable opportunity to translate research into practical impact.
Dr Hua’s research areas include Natural Language Processing (NLP), Large Language Models (LLMs), Knowledge Graphs, Dialogue Systems, Machine Learning, Deep Learning, Reinforcement Learning, and Causality.
