Yuan Sui

PhD student, National University of Singapore

Joined

May 2022

Names

Yuan Sui (Preferred)

Emails

****@gmail.com (Confirmed)

****@u.nus.edu (Confirmed)

Personal Links

Career & Education History

PhD student

National University of Singapore (u.nus.edu)

2023 – Present

Intern

Tencent AI Lab (tencent.com)

2025 – 2025

Intern

Microsoft Research Asia (microsoft.com)

2022 – 2023

Intern

Dartmouth College (dartmouth.edu)

2022 – 2023

Intern

Institute of Computing Technology, Chinese Academy of Sciences (ict.ac.cn)

2021 – 2022

Advisors, Relations & Conflicts

PhD Advisor

Bryan Hooi

Present

Expertise

Knowledge Graphs

LLMs

Reasoning

NLP

Present

Publications

What-If Analysis of Large Language Models: Explore the Game World Using Proactive Thinking
Yuan Sui, Yanming Zhang, Yi Liao, Yu Gu, Guohua Tang, Zhongqian Sun, Yang Wei, Bryan Hooi
- ICLR 2026 Workshop AIMS
- Readers: Everyone
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Tri Cao, Bennett Lim, Yue Liu, Yuan Sui, Yuexin Li, Shumin Deng, Lin Lu, Nay Oo, Shuicheng YAN, Bryan Hooi
- ICLR 2026 Poster
- Readers: Everyone
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Zifeng Ding, Shenyang Huang, Zeyu Cao, Emma Kondrup, Zachary Yang, Xingyue Huang, Yuan Sui, Moy Yuan, Yuqicheng Zhu, Xianglong Hu, Yuan He, Farimah Poursafaei, Michael M. Bronstein, Andreas Vlachos
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Think in Games: Learning to Reason in Games via Reinforcement Learning with Large Language Models
Yi Liao, Yu Gu, Yuan Sui, Zining Zhu, Yifan Lu, Guohua Tang, Zhongqian Sun, Yang Wei
- ICLR 2026 Conference Withdrawn Submission
- Readers: Everyone
Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
Zifeng Ding, Shenyang Huang, Zeyu Cao, Emma Kondrup, Zachary Yang, Xingyue Huang, Yuan Sui, Moy Yuan, Yuqicheng Zhu, Xianglong Hu, Yuan He, Farimah Poursafaei, Michael M. Bronstein, Andreas Vlachos
- NPGML Poster
- Readers: Everyone
Enabling Self-Improving Agents to Learn at Test Time With Human-In-The-Loop Guidance
Yufei He, Ruoyu Li, Alex Chen, Yue Liu, Yulin Chen, Yuan Sui, Cheng Chen, Yi Zhu, Luca Luo, Frank Yang, Bryan Hooi
- CoRR 2025
- Readers: Everyone
VPI-Bench: Visual Prompt Injection Attacks for Computer-Use Agents
Tri Cao, Bennett Lim, Yue Liu, Yuan Sui, Yuexin Li, Shumin Deng, Lin Lu, Nay Oo, Shuicheng Yan, Bryan Hooi
- CoRR 2025
- Readers: Everyone
Robustness via Referencing: Defending against Prompt Injection Attacks by Referencing the Executed Instruction
Yulin Chen, Haoran Li, Yuan Sui, Yue Liu, Yufei He, Yangqiu Song, Bryan Hooi
- CoRR 2025
- Readers: Everyone
FiDeLiS: Faithful Reasoning in Large Language Models for Knowledge Graph Question Answering
Yuan Sui, Yufei He, Nian Liu, Xiaoxin He, Kun Wang, Bryan Hooi
- BuildingTrust
- Readers: Everyone
Can Knowledge Graphs Make Large Language Models More Trustworthy? An Empirical Study Over Open-ended Question Answering
Yuan Sui, Yufei He, Zifeng Ding, Bryan Hooi
- BuildingTrust
- Readers: Everyone

View all 28 publications

Co-Authors

View all 68 co-authors