Chuan XIAO
Associate Professor
Osaka University / Nagoya University
Email: chuanx [at] ist.osaka-u.ac.jp / chuanx [at] nagoya-u.jp
Phone: +81-6-6105-6502
Address:
Graduate School of Information Science and Technology
Osaka University
1-5, Yamadaoka, Suita, Osaka 565-0871
Japan
News
Jellfish-7B/8B/13B: As a joint work with NEC, we released the 7B, 8B, and 13B models for data preprocessing, by fine-tuning Mistral-7B-Instruct-v0.2, Llama-3-8B-Instruct, and OpenOrca-Platypus2-13B, respectively. Our paper is available here, and the slides are available here. We released our instruction data here.
Shall we team up: Following the SABM framework, we discovered the spontaneous cooperation of LLM agents in competing environments. Source codes for case studies are available here.
PrivBench: We developed a privacy-preserving database synthesis method for benchmarking publishing. Source code is available here.
PEOs: Our paper on probabilistic routing in graph-based approximate nearest neighbor search (ANNS) has been accepted by ICML 2024. We proposed a fast ANNS framework with performance guarantees, jointly working with prevalent graph-based indexes. Source code will be released very soon!
LLMob: As a joint work with the University of Tokyo, we developed an LLM agent framework for the generation of personal activity trajectories. The source code is here.
Our paper, which investigates the application of Shannon entropy in assessing students' abstraction levels to optimize students' learning process, has been accepted in the IEEE Transactions on Education (ToE).
SABM: We developed a computer simulation framework that incorporates LLMs into agent-based modeling. We released the slides and source codes.
Short Biography
I am an associate professor with the Big Data Engineering Laboratory at Osaka University and a guest associate professor with the Database Laboratory at Nagoya University.
I graduated from the University of New South Wales in 2010, under the supervision of Xuemin Lin and Wei Wang.
Research
My research interests focus on artificial intelligence, computer simulation, data science, and natural language processing. In detail, I explore the following research fields:
Agent-based modeling
Computational social science
Data preprocessing
Foundation models
Multi-agent systems