Generative AI for High-Stakes Decisions with Societal Impact

Speaker: Dr. Lingkai KONG
Postdoctoral Fellow
Harvard John A. Paulson School of Engineering and Applied Sciences

Title: Generative AI for High-Stakes Decisions with Societal Impact

Date: Monday, 2 February 2026

Time: 9:30am - 10:30am

Join Zoom Meeting: https://hkust.zoom.us/j/96688516988?pwd=OnUqmxqUN3hMAnxHb3OamdsrQzc17d.1
Meeting ID: 966 8851 6988
Passcode: 202627

Abstract:

With rapid advances in machine learning, data-driven decision-making is increasingly used to guide high-stakes choices. Yet many methods break down in the real world, where data is imperfect, models are misspecified, and actions must be selected from large, constrained combinatorial spaces. My research develops reliable decision-making systems by integrating generative AI with optimization and reinforcement learning to produce policies that are more sample-efficient, robust, and feasible.

In this talk, I will first show how flow matching improves the sample efficiency of reinforcement learning by selectively reusing imperfect offline data. I will then present a framework that combines flow matching with an optimization solver to represent expressive policies over combinatorial action spaces while guaranteeing feasibility under real operational constraints. Throughout, I will highlight collaborations with field partners that translate these algorithmic ideas into impact—from environmental sustainability, including conservation planning in African national parks, to public health, including work with the WHO on optimizing HIV testing policies in South Africa.

I will conclude by outlining my vision for generative-AI-powered, interactive multi-stakeholder decision-making, and discuss how these advances can support applications that directly benefit Hong Kong society.

Biography:

Lingkai Kong is a Postdoctoral Fellow at the Harvard John A. Paulson School of Engineering and Applied Sciences. He earned his Ph.D. in Computational Science and Engineering from the Georgia Institute of Technology. His research advances generative AI by integrating it with optimization and reinforcement learning to address high-stakes decision-making challenges in public health and sustainability. Dedicated to bridging theory and practice, Lingkai collaborates closely with field partners to translate algorithmic innovations into tangible social impact. His work has been published in top-tier venues such as ICML, NeurIPS, and ICLR, and he has delivered tutorials at major data science conferences like KDD. He is also a recipient of the Otto & Jenny Krauss Fellowship.