Author

Bryan Hooi

Observed name: Hooi, Bryan

Institution: National University of Singapore

Observed institutions: University of Southern California, University of California, Merced, National University of Singapore

OpenAlex ID: A5093876095

Self-Supervised Aggregation of Diverse Experts for Test-Agnostic Long-Tailed Recognition

2022 · Yifan Zhang, Bryan Hooi, et al. · neural information processing systems · 101

PDF

MGNNI: Multiscale Graph Neural Networks with Implicit Layers

2022 · Juncheng Liu, Bryan Hooi, et al. · neural information processing systems · 10

PDF

Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models

2025 · Shuyang Hao, Bryan Hooi, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 4

PDF

How to Make Large Language Models Generate 100% Valid Molecules?

2025 · Wen Tao, Jing Tang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2

PDF

Con-ReCall: Detecting Pre-training Data in LLMs via Contrastive Decoding

2024 · Wang, Cheng, Wang, Yiwei, et al. · arXiv (Cornell University) · 2

PDF

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in Large Language Models

2024 · Hu, Zhiyuan, Liu, Chumin, et al. · arXiv (Cornell University) · 2

PDF

Beyond ’Aha!’: Toward Systematic Meta-Abilities Alignment in Large Reasoning Models

2026 · Zhiyuan Hu, Yibo Wang, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · 1

PDF

Enhancing LLM Character-Level Manipulation via Divide and Conquer

2025 · Xiong, Zhen, Cai, Yujun, et al. · arXiv (Cornell University) · 1

PDF

Tricking Retrievers with Influential Tokens: An Efficient Black-Box Corpus Poisoning Attack

2025 · Cheng Wang, Yiwei Wang, et al. · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · 1

PDF

From Approval to Abuse: Privilege Escalation Attacks on Harness-Protected Coding Agents

2026 · Yang, Xianglin, Zhang, Yechao, et al. · arXiv (Cornell University)

PDF

FrugalEvo: Towards Cost-Aware LLM-Guided Program Evolution

2026 · Chen, Hui, Qi, Xuan, et al. · arXiv (Cornell University)

PDF

When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent Debate

2026 · Xu, Duofeng, Hooi, Bryan, et al. · arXiv (Cornell University)

PDF

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

2026 · Ji, Shuo, Li, Yibo, et al. · arXiv (Cornell University)