Kailong Wang

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

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

Frequent co-authors

Zhibo Zhang (1)Yuxi Li (1)Ouyang Zhen (1)Ling Shi (1)

Papers (1)

May 28, 2026

3d 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

Search

Kailong Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)