Jianpeng Chen

About Me

I am currently a Ph.D. student in the Department of Computer Science at Virginia Tech since Aug. 2023, where I am advised by Prof. Dawei Zhou in VLOG Lab. During my M.S. degree at University of Electronic Science and Technology of China (UESTC), I was fortunately advised by Prof. Yazhou Ren and Prof. Lifang He on the topic of multi-view/graph self-supervised learning.

Generally, my research lies in data mining and machine learning, with a particular focus on self-/un-supervised multi-modal/view/graph learning. and Agentic LLMs. I also seek to apply my research to scientific domains, such as 3D graph modeling of metamaterials and molecules, contributing to the broader community of AI for science. To date, my work has led to multiple publications in top-tier venues, including KDD, AAAI, TNNLS, ICML, NAACL, etc., spanning machine learning, language models, and scientific discovery. Some major results are as follows:

• Agentic LLMs (Preprints’25: LinguaMate, ChemBOMAS) paves the way for collaboration between knowledge-driven agents and data-driven agents by exploring symbolic-driven latent optimization and finetuned LLM with Bayesian optimization.
• Multi-view/modal learning (ICML’25, AAAI’23, AAAI’24, ICONIP’22) studies unsupervised multi-view/modal alignment and collaboration mechanisms for clustering and generative tasks.
• Graph learning/generation (INS’24, TNNLS’25) develops methods for graph semantic extraction and specification-aware variational inference for graph generation.
• Applications on Molecular and Material Science (KDD’25, ICML’25, IJCAI’24) investigates how the advanced LLMs and generative models can be integrated with domain-specific knowledge for molecule and material modeling.

News

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

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

• [May 2026] I will attend North East AI Agents Day to present our work MetaSymbO, an agentic framework for metamaterial discovery. Let’s meet in NYC!

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

• [April 2026] I will join Google - YouTube Shorts Ranking as a PhD intern this summer, focusing on efficient inference and training for large-scale models.

Archived News →

Experience

• Google | PhD SWE+ Intern | YouTuBe May 2026 – Aug. 2026
  Optimizing large-scale model inference and training efficiency.
• Shanghai AI Laboratory | Research Intern | Physical Science Sep. 2023 – Dec. 2024
  AI for Science, with a focus on scientific machine learning and physical science applications.

Selected Publications

(Refer to Google Scholar for full publication list.)

Talks

• Accepted Talk (Integrating Heterogeneous Data, Computational Tools, and Visual Interface for Metamaterial Discovery) at Towards Agentic AI for Science, AAAI Spring Symposia 2025

Services

Conference PC/Reviewers

• Conference on Neural Information Processing Systems (NeurIPS) 2023, 2024, 2025
• International Conference on Learning Representations (ICLR) 2024, 2025
• International Conference on Machine Learning (ICML) 2025
• SIGKDD Conference on Knowledge Discovery and Data Mining DB Track (KDD) 2025
• AAAI Conference on Artificial Intelligence (AAAI) 2024, 2025
• International Conference on Artificial Intelligence and Statistics (AISTATS) 2025
• The International Conference on Neural Information Processing (ICONIP), 2021 - 2025

Journal Reviewers

• IEEE Transactions on Artificial Intelligence (TAI)
• IEEE Transactions on Neural Networks and Learning Systems (TNNLS)
• IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)
• Journal of Data-Centric Machine Learning Research (DMLR)
• Information Fusion
• Information Sciences

Powered by Jekyll and Minimal Light theme.