Lingkai Kong's website
Postdoctoral Fellow at Harvard University
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.
- Generative AI Against Poaching: Latent Composite Flow Matching for Wildlife Conservation, Arxiv
- LLM-based Agent Simulation for Maternal Health Interventions: Uncertainty Estimation and Decision-focused Evaluation, AAMAS-AASG’25
- PRIORITY2REWARD: Incorporating Healthworker Preferences for Resource Allocation Planning, AAAI’25
- When in Doubt: Neural Non-Parametric Uncertainty Quantification for Epidemic Forecasting, NeurIPS’21