研究成果

ShapleyLaw: A Game-Theoretic Approach to Multilingual Scaling Laws

Xuyang Cao, Qianying Liu, Chuan Xiao, Yusuke Oda, Jiayi Wang, Pontus Stenetorp, Daisuke Kawahara, Makoto Onizuka, Sadao Kurohashi, Shuyuan Zheng

Conference on Empirical Methods in Natural Language Processing (EMNLP)

2026年10月

Seven security challenges in cross-domain multi-agent LLM systems

Ronny Ko, Jiseong Chung, Shuyuan Zheng, Chuan Xiao, Tae-Wan Kim, Makoto Onizuka, Won-Yong Shin

npj Artificial Intelligence

2026年9月

DOI: 10.1038/s44387-026-00128-9

Adaptive Layer Selection for Layer-Wise Token Pruning in LLM Inference

Rei Taniguchi, Yuyang Dong, Makoto Onizuka, and Chuan Xiao

ACL Findings

2026年7月

LLM-Based Social Simulations Require a Boundary

Zengqing Wu, Run Peng, Takayuki Ito, Makoto Onizuka, and Chuan Xiao

ICML 2026

2026年7月

AKV: Agile Read-Efficiently Key-Value OLTP Engine for Non-Volatile Memory

Shuai Liu, Jianbin Qin, Tianyu Wang, Yuxing Chen, Anqun Pan, Rui Mao, Yuxuan Qiu, Makoto Onizuka, Chuan Xiao

IEEE Transactions on Knowledge and Data Engineering (TKDE)

2026年2月

DOI: 10.1109/TKDE.2025.3632295

巻・号・ページ: Vol. 38 , No. 2 , pp. 857 - 871