Zhe Zeng
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
ML×1AI×1Crypto×1
Frequent co-authors
Research Timeline
2026
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
MirageBackdoor introduces a novel, highly stealthy backdoor attack that forces Large Language Models to generate correct reasoning steps (Think Well) but output an incorrect final answer (Answer Wrong), bypassing existing detection methods.
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved expert utilization.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIRecentJun 1, 2026
ProbMoE: Differentiable Probabilistic Routing for Mixture-of-Experts
The paper introduces ProbMoE, a probabilistic routing framework that tackles the non-differentiability of top-$k$ routing in Mixture-of-Experts (MoE) models, achieving strong performance with improved…
View →
cs.CRRecentApr 8, 2026