📝 Publications

💡 Optimization and Control in Deep Learning

Published:

• Neurocomputing PIDNODES: Neural Ordinary Differential Equations Inspired by a Proportional-Integral-Derivative Controller
  Pengkai Wang* (co-first), Chen Song*, Jiaxu Liu, Chao Xu, Shengze Cai

• Nature Communications Accelerated optimization in deep learning with a proportion-integral-derivative controller
  Chen Song, Jiaxu Liu, Pengkai Wang, Chao Xu, Shengze Cai, Jian Chu

• IEEE Transactions on Network Science and Engineering Output Feedback-based Continuous-Time Distributed PID Optimization Algorithms
  Liu Jiaxu, Chen Song, Pengkai Wang, Cai Shengze, Xu Chao, Chu Jian

• China Automation Congress Nonlinear Learning Predictive Control of Fed-Batch Hydrogenation Reactor Based on Gaussian Process Regression
  Pengkai Wang, Tehuan Chen, Changchun Pan

Under review:

• IEEE Transactions on Neural Networks and Learning System Accelerated Decentralized Machine Learning on Heterogeneous Data
  Jiaxu Liu, Yixiao Qian, Pengkai Wang, Song Chen, Shengze Cai

✈️ AI for Scientific Computing

Published:

• AAAI 2025 AeroGTO: An Efficient Graph-Transformer Operator for Learning Large-Scale Aerodynamics of 3D Vehicle Geometries
  Pengwei Liu, Pengkai Wang (co-first), Xingyu Ren , Hangjie Yuan, Zhongkai Hao, Chao Xu, Shengze Cai, Dong Ni

• Acta Mechanica PiRD: Physics-informed Residual Diffusion for Flow Field Reconstruction
  Siming Shan, Pengkai Wang, Chen Song, Jiaxu Liu, Wen Yao, Chao Xu, Shengze Cai

Under review:

• NeurIPS 2025 Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data
  Xingyu Ren, Pengwei Liu, Pengkai Wang, Hangjie Yuan, Dong Ni

• Nature Communications An Efficient Graph-Transformer Operator for Learning Physical Dynamics with Manifolds Embedding
  Pengwei Liu, Xingyu Rena, Pengkai Wang* (co-first), Hangjie Yuan, Zhongkai Hao, Chao Xua, Dong Ni, Shengze Cai