Shang Zhu

Shang Zhu

Auto-generated profile, based on publicly available information

Shang Zhu

Department of Mechanical Engineering, University of Michigan, Ann Arbor, USA

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
29 September 2025 in Machine Learning: Science and Technology
Verified
Journal Article
Open access
YZYoel Zimmermann
Yoel Zimmermann
ABAdib Bazgir
Adib Bazgir
AAAlexander Al-Feghali
Alexander Al-Feghali
MAMehrad Ansari
Mehrad Ansari
JBJoshua Bocarsly
Joshua Bocarsly
BBBen Blaiszik
Ben Blaiszik
Large language models (LLMs) are reshaping many aspects of materials science and chemistry research, enabling advances in molecular property prediction, materials design, scientific automation, knowledge extraction, and more. Recent developments demonstrate that the latest class of models are able to integrate structured and unstructured data, assist in hypothesis generation, and streamline research workflows. To explore the frontier of LLM capabilities across the research lifecycle, we review applications of LLMs through 32 total projects developed during the second annual LLM hackathon for applications in materials science and chemistry, a global hybrid event. These projects spanned seven key research areas: (1) molecular and material property prediction, (2) molecular and material design, (3) automation and novel interfaces, (4) scientific communication and education, (5) research data management and automation, (6) hypothesis generation and evaluation, and (7) knowledge extraction and reasoning from the scientific literature. Collectively, these applications illustrate how LLMs serve as versatile predictive models, platforms for rapid prototyping of domain-specific tools, and much more. In particular, improvements in both open source and proprietary LLM performance through the addition of reasoning, additional training data, and new techniques have expanded effectiveness, particularly in low-data environments and interdisciplinary research. As LLMs continue to improve, their integration into scientific workflows presents both new opportunities and new challenges, requiring ongoing exploration, continued refinement, and further research to address reliability, interpretability, and reproducibility.

4 August 2023 in Green Chemistry
Verified
Journal Article
Closed access
PDF file
SZShang Zhu
Shang Zhu
BNBichlien H. Nguyen
Bichlien H. Nguyen
YXYingce Xia
Yingce Xia
KFKali Frost
Kali Frost
SXShufang Xie
Shufang Xie
JSJake A. Smith
Jake A. Smith
Rapid prediction of environmental chemistry properties is critical for the green and sustainable development of the chemical industry and drug discovery.

30 January 2023 in ACS Applied Materials & Interfaces
Verified
Journal Article
Open access
SZShang Zhu
Shang Zhu
ZHZijian Hong
Zijian Hong
ZAZeeshan Ahmad
Zeeshan Ahmad
VVVenkatasubramanian Viswanathan
Venkatasubramanian Viswanathan
The lithium-metal anode is one of the most promising candidates for "beyond-lithium-ion" batteries thanks to its high specific capacity and low negative electrochemical potential. However, the electrode-electrolyte interface instability hinders its commercialization in rechargeable batteries. During cycles of charging and discharging, the lithium-metal anode is electrochemically plated and stripped along with the morphological evolution, which determines the cycling performance. In this work, with a phase-field model, we computationally characterize the morphological evolution dynamics during the plating and stripping steps at the lithium-metal-electrolyte interface. Our model is valid in a wide range of lithium concentrations in liquid electrolytes by incorporating nonidealities of electrolyte solutions into the interfacial reaction kinetics. Intriguingly, at fast stripping, i.e., high discharging overpotential, we observe an unexpected localized recrystallization phenomenon in high-lithium-ion-concentration valley regions. This recrystallization phenomenon mitigates the overall reaction rate heterogeneity and provides a potential approach to improving the morphological stability. Furthermore, we systematically investigate the correlation between the recrystallization phenomenon and lithium-ion activity and draw a simplified phase diagram for the overpotential-dependent recrystallization.

17 March 2026 in Nature Communications
Verified
Journal Article
Open access
PDF file
CXChangwen Xu
Changwen Xu
SZShang Zhu
Shang Zhu
VVVenkatasubramanian Viswanathan
Venkatasubramanian Viswanathan
Predicting crystal properties is essential for understanding structure-property relationships and accelerating material discovery. However, conventional approaches like experimental measurements or density functional theory calculations are resource-intensive, limiting their scalability. While machine learning offers a promising alternative by learning complex structure-property relationships from data, existing models often rely on labeled data, adopt representations insufficiently capturing essential structural characteristics, and lack integration of physics, limiting their generalizability and interpretability. Here, we introduce CLOUD (Crystal Language mOdel for Unified and Differentiable materials modeling), a transformer-based framework trained on a Symmetry-Consistent Ordered Parameter Encoding (SCOPE) that encodes crystal symmetry, Wyckoff positions, and composition in a compact, coordinate-free string representation. Pre-trained on over six million crystals, CLOUD is fine-tuned on downstream tasks and achieves competitive performance across diverse material properties, demonstrating strong scaling with respect to data and model size. Furthermore, as a proof-of-concept of differentiable materials modeling, CLOUD is applied to predict the phonon-related properties by integrating with the Debye model. This approach enforces thermodynamic consistency and enables temperature-dependent property prediction without requiring additional data. These results demonstrate CLOUD’s potential as a scalable and physics-informed foundation model for crystalline materials, unifying symmetry-consistent representations with physics-grounded learning for property prediction and materials discovery.

29 November 2022 in ChemRxiv
Verified
Preprint
Open access
PDF file
SZShang Zhu
Shang Zhu
ZHZijian Hong
Zijian Hong
ZAZeeshan Ahmad
Zeeshan Ahmad
VVVenkatasubramanian Viswanathan
Venkatasubramanian Viswanathan
This version was mistakenly uploaded in violation of journal policy.