Lingkai Kong
孔令恺
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.
For more details, see my CV.
My long-term goal is to build generative AI agents that understand the world, work alongside people, and help us make the decisions that matter most. My research pursues this vision along three threads:
Generative models that act, not just generate. I combine reinforcement learning with diffusion models and LLMs to study reliable generative policies and long-horizon planning under uncertainty.
How autonomous agents, together with the people in the loop, learn, cooperate, and strategically interact, and the collective behavior that emerges.
Translating these methods into deployed systems for high-stakes domains such as public health and sustainability.
Selected publications
- 2026Latent Spherical Flow Policy for Reinforcement Learning with Combinatorial ActionsIn International Conference on Machine Learning (ICML) (Spotlight), 2026
- 2026Reward Shaping for Inference-Time Alignment: A Stackelberg Game PerspectiveIn International Conference on Machine Learning (ICML), 2026
- 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics DataIn Advances in Neural Information Processing Systems (NeurIPS), 2025 (Spotlight)
- 2025Diffusion Models as Constrained Samplers for Optimization with Unknown ConstraintsIn Artificial Intelligence and Statistics (AISTATS), 2025
- 2024Aligning Large Language Models with Representation Editing: A Control PerspectiveIn Advances in Neural Information Processing Systems (NeurIPS), 2024
- 2023AdaPlanner: Adaptive Planning from Feedback with Language ModelsIn Advances in Neural Information Processing Systems (NeurIPS), 2023
- 2022End-to-End Stochastic Optimization with Energy-based ModelIn Advances in Neural Information Processing Systems (NeurIPS), 2022 (Oral, 181/10411, top 1.76%)