Announcement of presentations and exhibits at the 2025 MRS Fall Meeting & Exhibit

Matlantis Corporation will be exhibiting at the 2025 MRS Fall Meeting & Exhibit, which will be held from November 30th to December 5th, 2025 (US Eastern Standard Time). Matlantis' APAC Customer Success Team Leader, Nagoya, will be giving an oral presentation and the company will also have a booth. There will also be presentations related to Matlantis from external organizations. Please see below for details.

Exhibition and booth information

Exhibition period: December 2nd - December 4th, 2025 (US Eastern Standard Time)
Location: Exhibit Hall C, Level 2 at the Hynes Convention Center
Booth: 602

Presentation Information

Presentation Title: Atomistic Simulations of Metals and Alloys Using Universal Graph Neural Network Interatomic Potentials

Date and Time: December 3, 2025, 11:30 AM – 11:45 AM (Eastern Standard Time)
Department: MT04.06 Metals and Alloys I
Room: Hynes, Level 3, Room 312
Session Type: Oral
Speaker: Akihiro Nagoya
Author: Akihiro Nagoya, Taku Watanabe
Overview: Atomistic simulations are essential for the research and development of metallic materials, providing atomic-level insights into interfaces, defects, and complex microstructures to support alloy design and process optimization. While Molecular Dynamics (MD) is widely used, classical force fields lack the necessary accuracy and transferability for chemically complex or non-equilibrium systems, and high-accuracy Density Functional Theory (DFT) is computationally prohibitive for large-scale MD simulations.

Machine learning interatomic potentials (MLIPs) have emerged as a powerful method offering near-DFT accuracy at a drastically reduced computational cost. The PreFerred Potential (PFP) is a graph neural network-based MLIP trained on a huge DFT dataset. Owing to its universality and robustness, PFP has been applied to various systems, including semiconductors, battery materials, catalysts, metal–organic frameworks, and metals and alloys. To enhance its efficiency, we recently developed LightPFP, a moment tensor potential trained on the PFP dataset. LightPFP is ten times faster than the original PFP, striking an optimal balance between accuracy and speed, which makes it ideal for large-scale Molecular Dynamics (MD) simulations of metallic systems.

In this study, we validated the accuracy of PFP by calculating thermodynamic properties of several simple metals, showing good agreement with DFT results reported in the literature. Then, we demonstrate the applicability of both PFP and LightPFP to MD simulations of mechanical and interfacial phenomena. These results highlight the universality and robustness of our MLIPs, establishing them as powerful tools for accelerating metals and alloys developments.

Akihiro Nagoya
APAC Customer Success Team Leader, Matlantis Corporation
After graduating from Osaka University, he worked as a researcher at Toyota Central R&D Labs., Inc. He spent approximately 15 years researching solar cell materials, platinum catalysts for fuel cells, first-principles calculations for two-dimensional materials, and MI using classical MD calculations for polymers. He then worked at the Central Technical Research Institute of ENEOS Corporation before joining Matlantis. He is currently primarily involved in calculations related to battery materials and metal materials.

External Collaborators’ Presentation

December 1, 2025

Presentation title: How Reliable Are Machine Learning Potentials? An Assessment of Uncertainty Estimation Methods in LightPFP
Date and Time: December 1, 2025, 11:45 AM – 12:00 PM (Eastern Standard Time)
Department: MT04.01 Machine Learning Potentials I
Room: Hynes, Level 3, Room 312
Session Type: Oral
Speaker: Nontawat Charoenphakdee
Author: Nontawat Charoenphakdee, Wenwen Li, Yuta Tsuboi, Junichi Ishida, Ju Li
Organization: Preferred Networks, inc., Matlantis Corporation, Massachusetts Institute of Technology

December 2, 2025

Presentation title: LLM Agent System for Autonomous Generation of 3D Atomic Structures from Textual Descriptions
Date and Time: December 2, 2025, 3:30 PM – 3:45 PM (Eastern Standard Time)
Department: MT06.04 Generative AI Meets Materials Modeling—Emerging Opportunities and Challenges IVI
Room: Hynes, Level 3, Room 309
Session Type: Oral
Speaker: Iori Kurata
Authors: Iori Kurata, Ryohto Sawada, Terumasa Shimada, Yuki Orimo, Hodaka Mori
Organization: Preferred Networks, Inc., ENEOS Holdings, Inc.

Presentation title: Development of r2SCAN Level Universal Neural Network Potential and Its Applications
Date and Time: December 2, 2025, 7:00 PM – 9:00 PM (Eastern Standard Time)
Department: MT04.05 Poster Session I: Integrating Machine Learning and Simulations for Materials Modeling I
Room: Hynes, Level 1, Hall A
Session Type: Poster
Speaker: So Takamoto
Authors: So Takamoto, Chikashi Shinagawa, Daiki Shintani, Katsuhiko Nishimra, Kohei Shinohara, Shigeru Iwase, Ju Li
Organization: Preferred Networks, Inc., Massachusetts Institute of Technology

December 4, 2025

Presentation Title: Enhancing Crystal Structure Prediction with r2SCAN-Level Universal Neural Network Potentials
Date and Time: December 4, 2025, 7:00 PM – 9:00 PM (Eastern Standard Time)
Department: MT03.09 Poster Session: Accelerated Materials Discovery Through Data-Driven AI and Automation
Room: Hynes, Level 1, Hall A
Session Type: Poster
Speaker: Kohei Shinohara
Authors: Kohei Shinohara, Hideaki Imamura, Katsuhiko Nishimra, Shuhei Watanabe, Kaoru Hisama, Chikashi Shinagawa, So Takamoto, Ju Li
Organization: Preferred Networks, Inc., Massachusetts Institute of Technology

Official information about the society is here (external site) >> 2025 MRS Fall Meeting & Exhibit