avatar

Jianpeng Chen

Ph.D. student
Virginia Tech
jianpengc[at]vt[dot]edu


About Me

I am a Ph.D. student in Computer Science at Virginia Tech, advised by Prof. Dawei Zhou in the VLOG Lab. My research develops efficient, data-aware foundation models and agentic AI systems, with a particular interest in long-context modeling, adaptive data selection, multimodal reasoning, and scientific discovery.

I build learning systems that connect graph and multimodal representation learning, generative modeling, and physics-grounded agents for materials and molecular science. My work has appeared at COLM, KDD, ACL, ICML, NAACL, AAAI, and TNNLS. In Summer 2026, I am a PhD SWE+ Intern at Google, working on training and inference efficiency for large-scale recommendation models.

01 Efficient Foundation Models

Long-context modeling, adaptive token/state selection, data-efficient training, and quality-efficiency tradeoffs.

02 Agentic AI for Science

LLM agents, symbolic latent optimization, physics-grounded verification, and scientific reasoning workflows.

03 Multimodal Graph Learning

Representation learning and generative modeling for multi-view graphs, metamaterials, and molecular structures.

News

Our paper MetaSymbO about natural language-guided multi-agent material design has been accepted to COLM 2026. See you in SF this October!

I am pleased to be awarded Sanghani Center Student Travel Grant from Sanghani Center and Summer 2026 TFP grant from Virginia Tech GPSS.

Two papers, DuetDA and MATRIX, about data efficient material science has been accepted to KDD 2026. Sincere thanks to all collaborators!

I will attend North East AI Agents Day to present our work MetaSymbO, an agentic framework for metamaterial discovery. Let’s meet in NYC!

Our work on Physics-Grounded Material Claim Verification has been accepted to ACL 2026. Many thanks to all collaborators. See you in San Diego!

I will join Google - YouTube Shorts Ranking as a PhD intern this summer, focusing on efficient inference and training for large-scale models.

Congrats that our paper on multi-view heterophilous graph learning, SMHGC, has been published in Pattern Recognition. Thanks to all collaborators!

Congratulations to our work, MATRIX: Stress-Testing LLM Reasoning in Materials Science, accepted by the ICLR AI4Mat.

Glad to be recognized by the IEEE ICDM Organizing Committee as a Student Volunteer and contribute to this inspiring community.

Congrats to Alex for our work, Generalizable Physics-Aware Refinement Framework for Metamaterial Design, receiving the IEEE ICDM UGHS Rising Star Award.

Congrats that our paper, The End of Trial-and-Error: A Vision for Generative Intelligence in Metamaterial Design, has been accepted by IEEE ICDM Bluesky.

My research topic on Metamaterial Discovery has been accepted by the ICDM PhD Forum. See you in DC.

I am pleased to receive the Virginia Tech Travel Award.

Our benchmark, MetamatBench, on Metamaterial Discovery, has been accepted by KDD 2025.

Our paper Unimate has been accepted by ICML 2025.

I will give a talk on Metamaterial at AAAI Spring Symposia 2025.

Our demo MetaScientist has been accepted by NAACL 2025.

Our paper VGMGC has been accepted by TNNLS.

Experience

Google

PhD SWE+ Intern, YouTube Shorts Ranking

Optimizing training and inference efficiency for large-scale recommendation models.

Shanghai AI Laboratory

Research Intern, Physical Science

Developed AI for Science methods for scientific machine learning and physical science applications.

Selected Publications

(Refer to Google Scholar for full publication list.)

  1. COLM 2026
    MetaSymbO: Multi-Agent Language-Guided Metamaterial Discovery via Symbolic Latent Evolution
    Jianpeng Chen, Wangzhi Zhan, Dongqi Fu, Junkai Zhang, Zian Jia, Ling Li, Wei Wang, Dawei Zhou
    Third Conference on Language Modeling
    PDF Code

  2. KDD 2026
    DuetDA: Decomposed and Dynamic Data Attribution with Model-State Gating for Accelerated Scientific Endeavors
    Jianpeng Chen, Wangzhi Zhan, Haohui Wang, Dongqi Fu, Dawei Zhou
    Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining AI4Science Track, 2026
    Code

  3. ACL 2026
    PhyVer: Physics-Grounded Material Claim Verification with Multi-Fidelity Physical Evidence
    Jianpeng Chen, Wangzhi Zhan (Equal Contribution), Haohui Wang, Brian Mayer, Dongqi Fu, Dawei Zhou
    The 64th Annual Meeting of the Association for Computational Linguistics -- System Demonstration, 2026
    PDF Code Project Page

  4. KDD 2025
    MetamatBench: Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery
    Jianpeng Chen, Wangzhi Zhan, Haohui Wang, Zian Jia, Jingru Gan, Junkai Zhang, Jingyuan Qi, Tingwei Chen, Lifu Huang, Muhao Chen, Ling Li, Wei Wang, Dawei Zhou
    Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining D&B Track, 2025
    PDF Code Project Page BibTex

  5. ICML 2025
    UniMate: A Unified Model for Mechanical Metamaterial Generation, Property Prediction, and Condition Confirmation
    Wangzhi Zhan, Jianpeng Chen, Dongqi Fu, Dawei Zhou
    Forty-second International Conference on Machine Learning, 2025
    Code

  6. TNNLS
    Variational Graph Generator for Multi-View Graph Clustering
    Jianpeng Chen, Yawen Ling, Jie Xu, Yazhou Ren*, Shudong Huang, Xiaorong Pu, Zhifeng Hao, S Yu Philip, Lifang He
    IEEE Transactions on Neural Networks and Learning Systems
    PDF Code BibTex

  7. Pattern Rec.
    SMHGC: Homophily-Agnostic Multi-View Heterophilous Graph Clustering
    Jianpeng Chen, Yawen Ling (Equal Contribution), Yazhou Ren*, Zichen Wen, Tianyi Wu, Shufei Zhang, Lifang He
    Pattern Recognition
    PDF BibTex

  8. IJCAI 2024
    3D-FuM: Benchmarking 3D Molecule Learning with Functional Groups
    Tingwei Chen, Jianpeng Chen (Equal Contribution), Dawei Zhou
    PDF

  9. AAAI 2023
    Dual Label-Guided Graph Refinement for Multi-View Graph Clustering
    Yawen Ling, Jianpeng Chen (Equal Contribution), Yazhou Ren*, Xiaorong Pu, Jie Xu, Xiaofeng Zhu, Lifang He
    PDF Code Oral Presentation

  10. ICONIP 2022
    Shared-Attribute Multi-Graph Clustering with Global Self-Attention
    Jianpeng Chen, Zhimeng Yang, Xiaorong Pu, Yazhou Ren*, Li Gao, Lifang He
    PDF Code BibTex LNCS AC=14.6%, Oral Presentation

  11. INS
    Customizing Graph Neural Network using Path Reweighting
    Jianpeng Chen, Yujing Wang (Equal Contribution), Ming Zeng (Equal Contribution), Zongyi Xiang, Bitan Hou, Yunhai Tong, Ole J Mengshoel, Yazhou Ren*
    Information Sciences
    PDF Code

Talks

Services

Conference PC/Reviewers

Journal Reviewers


Powered by Jekyll and Minimal Light theme.