Sikai Cheng | Georgia Institute of Technology

About Me

I am a Ph.D. student in Machine Learning at the Georgia Institute of Technology, advised by Prof. Pascal Van Hentenryck. My research focuses on machine learning and its integration with optimization. I have made several successful attempts in applying these methods to large-scale transportation systems, wireless communications, and robust decision-making under uncertainty. In addition, I explore the reasoning capabilities of large language models and investigate reinforcement learning approaches for multi-agent systems. [Google Scholar]

Before beginning my Ph.D., I earned a Master’s degree in Operations Research from the H. Milton Stewart School of Industrial and Systems Engineering (ISyE) at Georgia Tech, and a Bachelor’s degree in Data Science from The Chinese University of Hong Kong, Shenzhen.

I have been fortunate to collaborate with Prof. Xin Chen during my master’s studies, as well as Prof. Xinyun Chen and Prof. Pengyi Shi during my undergraduate studies.

Publications

Submitted for publication

Toward Reliable Generative AI with Conformal Prediction: A Survey

Bruys, T., Cheng, S., Moradi, A., Van Hentenryck, P., & Zandehshahvar, R.

Manuscript submitted for publication, 2026.

PDF

Submitted for publication

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

Li, X. et al. (77 authors, including Cheng, S.)

Manuscript submitted for publication, 2026.

PDF Code

Submitted for publication

Plan, Verify and Fill: A Structured Parallel Decoding Approach for Diffusion Language Models

Li, M., Jiang, H., Cheng, S., Fu, H., Cai, Y., Huang, B., Ye, T., Chen, X., & Van Hentenryck, P.

Manuscript submitted for publication, 2026.

PDF

TMLCN

CSI-4CAST: A Hybrid Deep Learning Model for CSI Prediction with Comprehensive Robustness and Generalization Testing

Cheng, S., Zandehshahvar, R., Zhao, H., Garcia-Ulloa, D. A., Villena-Rodriguez, A., Navarro Manchón, C., & Van Hentenryck, P.

IEEE Transactions on Machine Learning in Communications and Networking (TMLCN), 2026.

PDF Code Dataset

Preprint

DualSchool: How reliable are LLMs for optimization education?

Klamkin, M., Deza, A., Cheng, S., Zhao, H., & Van Hentenryck, P.

Preprint, 2025.

PDF Code

ICDM

SPOT: Spatio-Temporal Pattern Mining and Optimization for Load Consolidation in Freight Transportation Networks

Cheng, S., Hijazi, A., Konak, J., Erera, A., & Van Hentenryck, P.

Proceedings of the IEEE International Conference on Data Mining (ICDM), 2025.

PDF

M&SOM

Contextual stochastic optimization for omnichannel multi-courier order fulfillment under delivery time uncertainty

Ye, T., Cheng, S., Hijazi, A., & Van Hentenryck, P.

Manufacturing & Service Operations Management (M&SOM), 2025. Finalist, M&SOM Practice-based Research Competition.

PDF

NeurIPS Workshop

Emergent collective intelligence from massive-agent cooperation and competition

Chen, H., Tao, S., Chen, J., Shen, W., Li, X., Yu, C., Cheng, S., Zhu, X., & Li, X.

NeurIPS 2022 Deep RL Workshop, 2023.

PDF Code