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.

I will be on the academic job market for 2026. Please reach out if you think my background and experience could be a good fit for your institute.

Many real-world decisions are high stakes, time sensitive, and made under uncertainty. Traditional decision-making methods often struggle in these settings because of the large spatial and temporal scales involved. My research explores how generative AI can help improve decision-making by modeling uncertainty, capturing complex patterns, and supporting more reliable and efficient choices. By combining generative models with optimization and reinforcement learning, I aim to build tools that not only advance machine learning but also contribute to solving real-world problems in areas such as public health and biodiversity conservation.

Below are some example papers that focus on the technical aspects of this work:

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data, NeurIPS’25 (Spotlight)
Robust Optimization with Diffusion Models for Green Security, UAI’25
Diffusion Models as Constrained Samplers for Optimization with Unknown Constraints, AISTATS’25
Aligning Large Language Models with Representation Editing: A Control Perspective, NeurIPS’24
AdaPlanner: Adaptive Planning from Feedback with Language Models, NeurIPS’23
End-to-End Stochastic Optimization with Energy-Based Model, NeurIPS’22 (Oral)
SDE-Net: Equipping Deep Neural Networks with Uncertainty Estimates, ICML’20

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