Publications

You can also find my papers on Google Scholar.

Physics-guided diffusion distillation from the Phys-Instruct paper.

NeurIPS 2026

[1] Ultra Fast PDE Solving via Physics Guided Few-step Diffusion

Xiangrui Kong, Yueqi Wang, Haoyang Zheng, Weijian Luo, Guang Lin

Training pipeline from the DiDi-Instruct paper.

ICLR 2026

[2] Ultra-Fast Language Generation via Discrete Diffusion Divergence Instruct

Haoyang Zheng, Xinyang Liu, Xiangrui Kong, Nan Jiang, Zheyuan Hu, Weijian Luo, Wei Deng, Guang Lin

arXiv PDF OpenReview Code Project

Bayesian sampling and active learning from the BLADE paper.

MLST 2026

[3] BLADE: Bayesian Langevin Active Discovery with Replica Exchange for Identification of Complex Systems

Xiangrui Kong, Haoyang Zheng, Guang Lin

Machine Learning: Science and Technology.

arXiv PDF Journal

Selection bias illustration from the electricity service equity paper.

NeurIPS CRL 2023 · Workshop

[4] Detecting Electricity Service Equity Issues with Transfer Counterfactual Learning on Large-Scale Outage Datasets

Song Wei, Xiangrui Kong, Sarah A. Huestis-Mitchell, Shixiang Zhu, Yao Xie, Alinson Santos Xavier, Feng Qiu

Causal Representation Learning Workshop at NeurIPS.