Eric Qu

PhD Student at UC Berkeley

CV

ericqu [at] berkeley [dot] edu

🖋 About Me

I am a third-year CS PhD Student at UC Berkeley, Berkeley AI Research Lab (BAIR) and Lawrence Berkeley National Laboratory (LBNL), advised by Aditi Krishnapriyan. I received my B.Sc. with distinction in Data Science from Duke Kunshan University and Duke University. Previously, I worked as a visiting researcher at Meta FAIR, FAIR Chemistry Group, and earlier a research intern at Microsoft Research Asia, Shanghai AI/ML Group.

My research interest mainly falls on AI for Science. Specifically, I am focusing on improving Machine Learning Interatomic Potentials (MLIPs) architectures and applications by designing scalable and efficient models. More broadly, I am interested in combining ideas from mathematics with machine learning, and using machine learning to solve interdisciplinary problems.

🔥 News

• [Sep 2025] Our new AllScAIP model is at the top of the Open Molecules Leaderboard 🎉
• [Jan 2025] Lawrence Berkeley National Laboratory reported EScAIP in the news!
• [Sep 2024] Our new EScAIP model is accepted by NeurIPS 2024 🎉
• [Sep 2024] Joined as a visiting researcher at Meta FAIR!
• [Aug 2023] Starting my PhD at UC Berkeley!
[Jan 2024] Our work "CNN Kernels Can Be the Best Shapelets" is accepted by ICLR 2024! 🎉
[May 2023] Graduated from Duke Kunshan University with distinction! 🎓
[May 2023] Duke Kunshan University reported my undergrad story (in Chinese) here
[Jan 2023] Our work "Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer" is accepted (Spotlight) by ICLR'23! 🎉
[Oct 2022] Our work "Lorentz Direct Concatenation for Stable Training in Hyperbolic Neural Networks" is accepted (Poster) by NuerIPS'22 NeurReps Workshop! 🎉
[May 2022] Joined as a research intern in Microsoft Research Asia. 👨‍💼
[Jan 2022] Our work "Lorentzian Fully Hyperbolic Generative Adversarial Network" is now public on arXiv.
[Aug 2021] Times Higher Education (Duke Kunshan University) reported our work in the news here.
[Apr 2021] Our work "Quantifying Nanoparticle Assembly States in a Polymer Matrix through Deep Learning" is accepted by Macromolecules!
• Show/Hide More

📝 Publications

A recipe for scalable attention-based ML Potentials: unlocking long-range accuracy with all-to-all node attention

Submitted to ICLR 2026

Eric Qu, Brandon Wood, Aditi Krishnapriyan, Zachary Ulissi

Paper

The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains

NeurIPS 2024 Poster

Eric Qu, Aditi Krishnapriyan

Paper Code

CNN Kernels Can Be the Best Shapelets

ICLR 2024 Poster

Eric Qu, Yansen Wang, Xufang Luo, Wenqiang He, Kan Ren, Dongsheng Li

Paper Code

Hyperbolic Kernel Convolution: A Generic Framework

Learning on Graphs Conference 2024

Eric Qu, Lige Zhang, Habib Debaya, Yue Wu, Dongmian Zou

Paper Code Poster

Autoencoding Hyperbolic Representation for Adversarial Generation

Transactions on Machine Learning Research (2024)

Eric Qu, Dongmian Zou

Paper Code Slides

Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer

ICLR 2023 Spotlight

Eric Qu, Xufang Luo, Dongsheng Li

Paper Code Slides Poster

Lorentz Direct Concatenation for Stable Training in Hyperbolic Neural Networks

NeurIPS 2023, NeurReps Workshop

Eric Qu, Dongmian Zou

Paper Poster

Quantifying Nanoparticle Assembly States in a Polymer Matrix through Deep Learning

Macromolecules, 54 (7), 3034-3040, (2021)

Eric Qu, Andrew Matthew Jimenez, Sanat K. Kumar, Kai Zhang

Paper Code Dataset

In-situ AFM tracking of Nanoparticle Diffusion in Semicrystalline Polymers

ACS Macro Lett. 2022, 11, 6, 818–824, (2022)

Kamlesh Bornani, Nico Mendez, Abdullah S. Altorbaq, Alejandro Muller, Max Yueqian Lin, Eric Qu, Kai Zhang, Sanat K. Kumar, Linda S. Schadler

Paper Code

💬 Talks

• The Importance of Being Scalable: Improving the Speed and Accuracy of Neural Network Interatomic Potentials Across Chemical Domains
  Virtual, SciML Symposium @ Georgia Tech 2024
  Kunshan, China, Learning on Graphs Conference Local Meetups 2024

• Stable Hyperbolic Neural Networks for Graph Generation and Classification
  Tokyo, Japan, ICIAM 2023 Mathematics of Geometric Deep Learning Minisymposium

• Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer
  Kigali, Rwanda, ICLR 2023 Spotlight Presentation, Oral 6 Track 5: Applications & Deep Learning

🏆 Awards and Honors

• [2024.5] NERSC GenAI for Science CFP Award (2500 GPU hrs) - U.S. Department of Energy
• [2023.10] Open Catalyst Challenge 3rd Place - NeurIPS 2023 Competitions
• [2023.5] Graduation with Distinction (Top 5%) - Duke Kunshan University
• [2023.5] Graduation with Latin Honors cum laude - Duke Kunshan University
• [2023.5] Zu Chongzhi Math Signature Work Award - Duke Kunshan Zu Chongzhi Math Center
[2023.5] Conference Travel Grant (ICLR 2023) - Duke Kunshan University
[2022.11] Conference Travel Grant (NeurIPS 2022) - Duke Kunshan University
[2022.6, 2020.6] Summer Research Scholar - Duke Kunshan University
[Fall 2019, Fall 2020, Sring 2021, Fall 2021, Spring 2022] Dean's List - Duke Kunshan University
[2020.4] Honorable Mention - Mathematical Contest In Modeling
[2019.3] Top 5% (Top 2 China Region) - Canadian Computing Competition Senior Division
[2016, 2017] First Prize (Top 20 in Shandong Province) - China National Olympiad in Informatics Senior Group
• Show/Hide More

📖 Educations

• 2023.8 - present  PhD Student in Computer Science, University of California, Berkeley

• 2019.8 - 2023.5   Dual Degree Undergraduate in Data Science, Duke Kunshan University / Duke University

🏢 Work Experiences

• 2024.9 - 2025.9  Meta FAIR, FAIR Chemistry Group

• 2022.5 - 2022.9  Microsoft Research, Shanghai AI/ML Group

• 2023.1 - 2023.6  Microsoft Research, Shanghai AI/ML Group

🏫 Services

• Reviewer/PC Member: NeurIPS {2023, 2024, 2025}, ICLR {2024, 2025, 2026}, ICML {2024, 2025}, AISTATS {2025, 2026}

• Journal Reviewer: TNNLS