Chen Wang

Ph.D. Student, Institute of Computing Technology, CAS

Hi, I'm Chen!

I am a Ph.D. student at the State Key Lab of Processors, ICT, CAS, advised by Prof. Weile Jia. My research focuses on AI for Science and High-Performance Computing, developing efficient learning methods and computing systems for atomistic simulation and materials design.

Chen Wang's avatar

Education

Publications

AI for Science

Structural alignment, pruning, and retraining for SO(3) equivariant models

Compact SO(3) Equivariant Atomistic Foundation Models via Structural Pruning

Chen Wang, Siyu Hu, Guangming Tan, Weile Jia

NeurIPS 2026 CCF A Oral

Panel (b) showing ELoRA's low-rank adaptation of an equivariant tensor product

ELoRA: Low-Rank Adaptation for Equivariant GNNs

Chen Wang, Siyu Hu, Guangming Tan, Weile Jia

ICML 2025 CCF A

Distillation of atomic energies and energy Hessians

Architecture-agnostic knowledge distillation for machine-learning interatomic potentials

Chen Wang, Siyu Hu, Guangming Tan, Weile Jia

Neural Networks 2027 CCF B

Two OMC-bench tasks and their dataset distributions

OMC-bench and AtomBit-OMC: task-aligned benchmarks and robust, interpretable machine-learned interatomic potentials for organic molecular crystals

Muyu Lu†, Chengxi Zhao†, Siyu Hu†, Danyang Chen†, Chen Wang†, Yixi Zhang, Yaolong Zhang, Man Luo, Fan Yu, Zhuoying Zhu, Bin Jiang, Guangming Tan, Weile Jia, Jun Jiang, Linjiang Chen († equal contribution)

npj Computational Materials 2026 JCR Q1

Lithium migration paths in LGPS

Constructing machine learning interatomic potentials with minimum amount of ab initio data

Wentao Zhang, Xingxing Wu, Chen Wang, Siyu Hu, Yueyang Liu, Lin-Wang Wang

npj Computational Materials 2026 JCR Q1

Two-stage workflow for equivariant fine-tuning and synthetic data generation

A Two-Stage Equivariant Training Framework Enables Quantum-Accurate Force Fields with Reduced DFT Training Data

Si-Yu Hu, Jie Zhu, Chen Wang, Lin-Wang Wang, Hong-Liang Liu, Wei-Le Jia, Guang-Ming Tan

Journal of Computer Science and Technology 2026 CCF B

Molecular structure and packing in the reversible polymorphic transition

Efficient fine-tuning of foundation atomistic models for reversible polymorphic phase transitions in organic molecular crystals

Muyu Lu, Siyu Hu, Chengxi Zhao, Chen Wang, Weile Jia, Guangming Tan, Jun Jiang, Linjiang Chen

Chinese Chemical Letters 2026 JCR Q1

High-Performance Computing

Flux workload prediction and distributed scheduling

Flux: Online, Fine-Grained Data Scheduling for Training Machine Learning Interatomic Potentials

Yuanchang Zhou, Chen Wang, Hongtao Xu, Mingzhen Li, Guangming Tan, Weile Jia

NeurIPS 2026 CCF A

MatterScale workflow with the LAMMPS loop, graph construction, M3GNet forward and backward passes, and force writeback

MatterScale: Scaling Foundation Machine Learning Interatomic Potentials for Billion-Atom Molecular Dynamics on the Next-Generation Supercomputer

Xiangyu Zhang, Junwei Feng, Jielan Li, Chen Wang, Yan Wang, Yusu Zhang, Hongxia Hao, Wei Hu, Weile Jia

SC 2026 CCF A

Atomic inputs and graph representations used by CHGNet

FastCHGNet: Training One Universal Interatomic Potential to 1.5 Hours with 32 GPUs

Yuanchang Zhou, Siyu Hu, Chen Wang, Lin-Wang Wang, Guangming Tan, Weile Jia

IPDPS 2025 CCF B

Comparison of the conventional SO(2) dataflow and the fused TrimSO(2) dataflow

TrimSO(2): Fast and Memory-Efficient Training of Equivariant Interatomic Potentials

Chen Wang, Yuanchang Zhou, Guangming Tan, Mingzhen Li, Weile Jia

arXiv 2026

GPU execution workflow for speculative crystal sampling

Accelerating Diffusion-Based Crystal Generation through Efficient Speculative Sampling

Chen Wang, Yuanchang Zhou, Siyu Hu, Mingzhen Li, Guangming Tan, Weile Jia

NPC 2026 CCF C

LunaTP overview showing node-centric execution, path grouping, and product and coefficient reuse

LunaTP: Enabling Efficient and Scalable Tensor Product for Equivariant MLIPs

Yuanchang Zhou, Mingzhen Li, Chen Wang, Xiangyu Zhang, Guangming Tan, Weile Jia

arXiv 2026

Overview of the MatRIS-MoE model and distributed training optimizations in Janus

Breaking the Training Barrier of Billion-Parameter Universal Machine Learning Interatomic Potentials

Yuanchang Zhou†, Hongyu Wang†, Yiming Du†, Yan Wang†, Mingzhen Li†, Siyu Hu†, Xiangyu Zhang, Weijian Liu, Chen Wang, Zhuoqiang Guo, Long Wang, Jingde Bu, Yutong Lu, Guangming Tan, Weile Jia († equal contribution)

arXiv 2026

Awards

Academic Competitions

  • Chinese Mathematics Competitions for College Students

    2022

    Provincial First Prize (Non-Mathematics Track)

  • Chinese Chemistry Olympiad

    2019

    First Prize (Preliminary Round)

Honors

  • Merit Student

    2025
  • Outstanding Graduate

    2024

    University of Science and Technology of China

  • National Scholarship

    2023
  • Shenzhen Stock Exchange Scholarship

    2022
  • National Encouragement Scholarship

    2021
  • Outstanding Freshman Scholarship

    2020

Service