activity
20242026
collaborators

13 papers

cond-mat.mtrl-sci2026

Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates

Zeyu Wang, Shuya Yamazaki, Martin Hoffmann Petersen +11

The appearance of generative models has opened vast chemical spaces in the design of functional materials. Although machine learning interatomic potentials (MLIPs) have substantial…

cs.RO2026

GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning

Jonas le Fevre Sejersen, Toyotaro Suzumura, Erdal Kayacan

This paper presents a novel approach to multi-robot collision avoidance that integrates global path planning with local navigation strategies, utilizing attentive graph neural netw…

cs.IR2026

Modeling User Preferences as Distributions for Optimal Transport-Based Cross-Domain Recommendation under Non-Overlapping Settings

Ziyin Xiao, Toyotaro Suzumura

Cross-domain recommender (CDR) systems aim to transfer knowledge from data-rich domains to data-sparse ones, alleviating sparsity and cold-start issues present in conventional sing…

cond-mat.mtrl-sci2025

Database and deep-learning scalability of anharmonic phonon properties by automated brute-force first-principles calculations

Masato Ohnishi, Tianqi Deng, Pol Torres +16

Understanding the anharmonic phonon properties of crystal compounds -- such as phonon lifetimes and thermal conductivities -- is essential for investigating and optimizing their th…

cs.IR2025

SymCERE: Symmetric Contrastive Learning for Robust Review-Enhanced Recommendation

Toyotaro Suzumura, Hisashi Ikari, Hiroki Kanezashi +2

Modern recommendation systems fuse user behavior graphs and review texts but often encounter a "Fusion Gap" caused by False Negatives, Popularity Bias, and Signal Ambiguity. We pro…

cs.IR2025

NewsReX: A More Efficient Approach to News Recommendation with Keras 3 and JAX

Igor L. R. Azevedo, Toyotaro Suzumura, Yuichiro Yasui

Reproducing and comparing results in news recommendation research has become increasingly difficult. This is due to a fragmented ecosystem of diverse codebases, varied configuratio…