Lingkai Kong's website

lingkaikong@g.harvard.edu

Welcome to Lingkai Kong (孔令恺)’s homepage! I am a postdoctoral fellow at Harvard, advised by Prof. Milind Tambe. I obtained my Ph.D. in Computational Science and Engineering from Georgia Institute of Technology, advised by Prof. Chao Zhang.

My research focuses on using generative AI to support reliable decision-making in high-stakes domains. I work closely with public-sector partners in public health and wildlife conservation, where data is often messy, incomplete, and decisions need to be made quickly across large spatial and temporal scales. These settings pose two major challenges: (1) How to represent uncertainty in complex environments to make risk assessments more reliable. (2) How to perform efficient optimization to guide effective decisions in real time.

My goal is to create generative AI methods that can turn complex, uncertain data into reliable and actionable decisions at scale. Below are some example papers that focus on the technical aspects of this work:

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data, Arxiv
Robust Optimization with Diffusion Models for Green Security, UAI’25
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints, AISTATS’25
AdaPlanner: Adaptive Planning from Feedback with Language Models, NeurIPS’23
End-to-End Stochastic Optimization with Energy-Based Model, NeurIPS’22

I work closely with domain experts to ensure that the methods I design address domain-specific challenges and deliver meaningful impact in practice.