Yang Jeong Park

Yang Jeong Park

Auto-generated profile, based on publicly available information

Yang Jeong Park

Department of Nuclear Science and Engineering, Massachusetts Institute of Technology, Cambridge, USA

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
4 March 2026 in Materials Horizons
Verified
Journal Article
Open access
PDF file
HLHeeseung Lee
Heeseung Lee
HYHyuk Jun Yoo
Hyuk Jun Yoo
HJHye Su Jang
Hye Su Jang
BPByeongho Park
Byeongho Park
YPYang Jeong Park
Yang Jeong Park
SHSang Soo Han
Sang Soo Han
This work outlines six defining characteristics of Self-Driving Laboratory (SDL) 2.0: interoperable, collaborative, generalizable, orchestrated, safe, and creative, forming a framework for next-generation autonomous laboratories.

14 July 2025 in Nature Energy
Verified
Journal Article
Closed access
PDF file
HXHongbin Xu
Hongbin Xu
YPYang Jeong Park
Yang Jeong Park
ZRZhichu Ren
Zhichu Ren
DZDaniel J. Zheng
Daniel J. Zheng
DMDavide Menga
Davide Menga
JLJu Li
Ju Li

4 December 2023 in Nature Computational Science
Verified
Journal Article
Closed access
PDF file
YPYang Jeong Park
Yang Jeong Park
HKHyunGi Kim
HyunGi Kim
JJJeonghee Jo
Jeonghee Jo
SYSungroh Yoon
Sungroh Yoon

28 September 2024 in Scientific Data
Verified
Journal Article
Open access
PDF file
YPYang Jeong Park
Yang Jeong Park
SJSung Eun Jerng
Sung Eun Jerng
SYSungroh Yoon
Sungroh Yoon
JLJu Li
Ju Li
The advent of artificial intelligence (AI) has enabled a comprehensive exploration of materials for various applications. However, AI models often prioritize frequently encountered material examples in the scientific literature, limiting the selection of suitable candidates based on inherent physical and chemical attributes. To address this imbalance, we generated a dataset consisting of 1,453,493 natural language-material narratives from OQMD, Materials Project, JARVIS, and AFLOW2 databases based on ab initio calculation results that are more evenly distributed across the periodic table. The generated text narratives were then scored by both human experts and GPT-4, based on three rubrics: technical accuracy, language and structure, and relevance and depth of content, showing similar scores but with human-scored depth of content being the most lagging. The integration of multimodal data sources and large language models holds immense potential for AI frameworks to aid the exploration and discovery of solid-state materials for specific applications of interest.

23 February 2025 in arXiv
Verified
Preprint
Open access
PDF file
YPYang Jeong Park
Yang Jeong Park
MKMayank Kumaran
Mayank Kumaran
CHChia-Wei Hsu
Chia-Wei Hsu
EOElsa Olivetti
Elsa Olivetti
JLJu Li
Ju Li
Artificial intelligence (AI) is increasingly used for the inverse design of materials, such as crystals and molecules. Existing AI research on molecules has integrated chemical structures of molecules with textual knowledge to adapt to complex instructions. However, this approach has been unattainable for crystals due to data scarcity from the biased distribution of investigated crystals and the lack of semantic supervision in peer-reviewed literature. In this work, we introduce a contrastive language-crystals model (CLaC) pre-trained on a newly synthesized dataset of 126k crystal structure-text pairs. To demonstrate the advantage of using synthetic data to overcome data scarcity, we constructed a comparable dataset extracted from academic papers. We evaluate CLaC's generalization ability through various zero-shot cross-modal tasks and downstream applications. In experiments, CLaC achieves state-of-the-art zero-shot generalization performance in understanding crystal structures, surpassing latest large language models.

23 June 2025 in arXiv
Verified
Preprint
Open access
PDF file
SKSo Yeon Kim
So Yeon Kim
YPYang Jeong Park
Yang Jeong Park
JLJu Li
Ju Li
Large-scale foundation models, including neural network interatomic potentials (NIPs) in computational materials science, have demonstrated significant potential. However, despite their success in accelerating atomistic simulations, NIPs face challenges in directly predicting electronic properties and often require coupling to higher-scale models or extensive simulations for macroscopic properties. Machine learning (ML) offers alternatives for structure-to-property mapping but faces trade-offs: feature-based methods often lack generalizability, while deep neural networks require significant data and computational power. To address these trade-offs, we introduce HackNIP, a two-stage pipeline that leverages pretrained NIPs. This method first extracts fixed-length feature vectors (embeddings) from NIP foundation models and then uses these embeddings to train shallow ML models for downstream structure-to-property predictions. This study investigates whether such a hybridization approach, by ``hacking" the NIP, can outperform end-to-end deep neural networks, determines the dataset size at which this transfer learning approach surpasses direct fine-tuning of the NIP, and identifies which NIP embedding depths yield the most informative features. HackNIP is benchmarked on Matbench, evaluated for data efficiency, and tested on diverse tasks including \textit{ab initio}, experimental, and molecular properties. We also analyze how embedding depth impacts performance. This work demonstrates a hybridization strategy to overcome ML trade-offs in materials science, aiming to democratize high-performance predictive modeling.