news

2025/07	Our paper MolGuidance, a follow-up work of PropMolFlow, has been accepted in ICML 2025 Generative AI for Biology (GenBio) Workshop. In this work, we integrate three advanced property‐guidance strategies—classifier‐free guidance, autoguidance, and model guidance—into an SE(3)‐equivariant flow‐matching framework for conditional molecule generation.
2025/05	Our PropMolFlow framework—now available online—uses flow matching parameterized by an SE(3)-equivariant graph neural network for conditional molecular generation. We demonstrate competitive performance against state-of-the-art diffusion models across a range of molecular properties, while maintaining high structural validity, stability, and sampling efficiency. To support reproducibility and further research, we also release two datasets: (1) DFT-computed properties for molecules generated with PropMolFlow, and (2) an updated QM9 SDF file (based on the DeepChem release) in which all bond-order and charge inconsistencies have been corrected.
2025/01	I officially joined University of Florida Department of Chemistry as a postdoc to work on molecular-graph generative modeling and AI-driven computational simulations.
2024/12	Our work “Data-efficient and interpretable inverse materials design using a disentangled variational autoencoder” is published on line at AI & Materials. We employed disentangled variational autoencoder to develop a data-efficient and interpretable inverse materials design approach, which also has the potential of design materials with multiple target properties.
2024/09	I am thrilled to announce that our preprint for inverse materials design using a disentangled variational autoencoder is available at arXiv.
2024/07	I attended the NIST AI for Materials Science (AIMS) 2024 workshop in Rockville, MD and presented a poster for our work “machine learning accelerated discovery of corrosion-resistant high-entropy alloys”.
2024/07	Our paper “Dynamic stability of Pt-based alloys for fuel-cell catalysts calculated from atomistics” is accepted into Catalysis Science & Technology. It is out here.
2024/06	Our full proposal “CHARMED: Collaborative Human-AI to Revolutionize Materials Exploration and Discovery” has been submitted to NSF ACED program. It proposes to innovate probabilistic models and intelligent user interface for data-efficient and interpretable inverse materials design for complex materials such as high-entropy alloys.
2024/06	Our paper “Measuring wake deflection from SCADA data during wake steering using machine learning” was published at Journal of Physics: Conference Series for the TORQUE 2024 conference. Now it is available here.
2024/04	Our full proposal “Physics and Mechanics of Brittle Particle Cold Spray via Machine Learning enabled Multiscale Simulaitons” has been submitted to NSF Advanced Manufacturing Program in response to a Dear College Letter: Funding Opportunities for Engineering Research in Artificial Intelligence. It proposes to use integrated machine learning assisted simulations and experiments to overcome fundamental challenges for brittle particle cold spray, a novel additive manufacturing technique. I led the ideation and drafting of material simulations and machine learning methods for this proposal.
2024/02	I am thrilled to announce that our work “Machine learning accelerated discovery of corrosion-resistant high-entropy alloys” has been published in Computational Materials Science.
2024/02	I gave a virtual seminar at Worcester Polytechnic Institute (WPI) Mechanical & Materials Engineering graduate seminar on Feb 21, 2024 about “Rational Design of Nanoalloy Electrocatalysts”.
2023/12	My perspective about trends of 2024 AI in materials science research has been posted on EAI webpage .
2023/12	Our work on combining nearsighed force training and global optimization techniques to understand Co-Pt nanoparticle phase stability has been published at JPCC .
2023/11	I presented a poster on “Challenges and Opportunities for Machine Learning Accelerated Materials Qualification for Brittle Particle Cold Spray” at the MRS 2023 Fall Meeting & Exhibit. Also, Zachery Hindley, a summer intern at the Roux Engineering team comentored by me and Nathan Post, presented a talk for his internship work regarding “Image Selection for Atomistic Machine Learning using an Autoencoder”.
2023/07	Excited to announce that our work on materials design for corrosion-resistant high-entropy alloys with machine learning is out at arXiv.
2023/06	Thrilled to share that our work on nanoparticle alloy phase stability using NFT is now available on arXiv.
2023/05	I presented a poster at the ICME2023 conference in Orlando for our work titled “Machine learning accelerated discovery of corrosion-resistant high-entropy alloys”.
2023/05	I recorded a MOOC lecture titled “AI in Engineering” with the Experiential Digital Global Education team.
2023/01	I gave a talk at the Roux weekly academic workshop for one piece of my PhD work on nanoparticle phase stability. Slides can be found here.
2022/12	Our work on general strain trends in catalysis is published on J. Phys. Chem. C.
2022/11	I joined the Roux Institute of Northeastern University as a Experiential AI postdoc. I will work on machine learning accelerated materials design and data analytic approaches in additive manufacturing.
2022/07	I defended my PhD thesis. The thesis is available at Brown library and ProQuest. Slides are here.
2022/02	I gave a talk for our nearsighted force-training work at the New England Catalysis Winter meeting.
2022/01	Out work using nearsighted force-training to curate training data only when necessary is out on J. Chem. Phys.
2021/06	I am honored to be selected by SIGMA XI Honor Society as a full member.
2020/10	Our work using eigenforce model to predict the anisotropic strain effect of Pt ternary alloys has been published on JACS.
2020/07	I won a solo gold metal (5/1621) for the Kaggle competition Jigsaw Multilingual Toxic Comment Classification. I became a Kaggle competition master with one gold and two silver medals.
2020/06	I won a solo silver metal (90/2225) for the Kaggle competition Tweet Sentiment Extraction.
2020/04	I won a silver metal (90/2059) as the team leader for the Kaggle competition Bengali.AI Handwritten Grapheme Classification.
2019/03	I am delighted to announce that I have been selected to participate in the open graduate education program.
2019/01	We introduced eigenforce model to quantify strain effect for adsorption energy and employed that to understand the oxygen reduction catalytic performance of face-centered cubic Pt–Co and Pt–Fe alloys. The work is now published at J. Chem. Phys.