Yuxi Li

Huazhong University of Science and Technology, Wuhan, China

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Red-Teaming & Adversarial Robustness (2)Architecture Design (Transformers, SSMs, MoE) (1)RLHF & Preference Learning (1)Constitutional AI & AI Ethics (1)

Frequent co-authors

Zhibo Zhang (2)Ouyang Zhen (1)Ling Shi (1)Kailong Wang (1)

Papers (2)

May 28, 2026

2w ago·also Beihang

Understanding Safety-Sensitive Expert Behavior in Mixture-of-Experts LLMs

Safety in MoE LLMs isn't about routing harmful requests to "refusal experts"—it's surprisingly localized within specific experts, and you can break it without significantly changing the model's overall routing behavior.

Zhibo Zhang, Yuxi Li, Ouyang Zhen +2

Architecture Design (Transformers, SSMs, MoE)Red-Teaming & Adversarial Robustness RLHF & Preference Learning

Apr 1, 2026

Jiaqing Li +4Apr 1, 2026·also Hubei University, HUST

When Safe Models Merge into Danger: Exploiting Latent Vulnerabilities in LLM Fusion

Merging seemingly safe LLMs can create dangerously misaligned models, thanks to a new "TrojanMerge" attack that exploits latent vulnerabilities.

Jiaqing Li, Zhibo Zhang, Shide Zhou +2

Constitutional AI & AI Ethics Open-Source Models & Weights Red-Teaming & Adversarial Robustness

Search

Yuxi Li

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (2)