OMRON SINIC X Corporation (Headquarters: Bunkyo-ku, Tokyo; President and CEO: Masaki Suwa; hereinafter referred to as "OSX") is pleased to announce that a research paper by Senior Researcher Tatsunori Taniai, among others, has been accepted for the Twelfth International Conference on Learning Representations (ICLR 2024).

Along with NeurIPS¹⁾ and ICML²⁾, ICLR is one of the premier international conferences in the machine learning field. A total of 2,261 papers (About 31%) were accepted out of 7,262 submissions in 2024. The conference will take place in Vienna, Austria, from May 7 to 11, 2024. Our paper accepted for ICLR 2024 presents a simple yet effective Transformer-based encoder architecture for crystal structures, called Crystalformer, which can bridge physics and machine learning through a new concept of neural potential summation.

1) Neural Information Processing Systems
2) International Conference on Machine Learning

■Paper accepted for ICLR 2024

Title	Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
Authors	Tatsunori Taniai (OSX), Ryo Igarashi (OSX), Yuta Suzuki (TOYOTA MOTOR CORPORATION), Naoya Chiba (Tohoku University), Kotaro Saito (Randeft Inc., Osaka University), Yoshitaka Ushiku (OSX), Kanta Ono (Osaka University)
Related page	https://omron-sinicx.github.io/crystalformer/

※Affiliation at the time of submission

For a list of OSX's publications, please visit
https://www.omron.com/global/en/technology/publications/?affiliation=%5B%22OSX%22%5D

About OMRON SINIC X Corporation
OMRON SINIC X Corporation is a strategic subsidiary seeking to realize the "near future designs" that OMRON forecasts. It is comprised of researchers with cutting-edge knowledge and experience across a wide range of technological domains, including AI, Robotics, IoT, and sensing. With the aim of addressing social issues, OSX integrates innovative technologies with business models and strategies in technology and IP to create near-future designs. Additionally, the company accelerates the creation of these designs through collaborative research with universities and external research institutions. For more details, please refer to https://www.omron.com/sinicx/en/

OMRON SINIC X Research Paper Accepted for ICLR 2024, the Premier International Conference on Machine Learning

OMRON SINIC X Research Paper Accepted for ICLR 2024, the Premier International Conference on Machine　Learning