Xiuchao Sui
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1NLP×1
Frequent co-authors
Research Timeline
2026
Confidence-Adaptive SwiGLU for Mixture-of-Experts
The paper introduces Confidence-Adaptive SwiGLU ($κ$-SwiGLU), a novel gating mechanism for Mixture-of-Experts (MoE) models that dynamically adjusts the gate sharpness based on token-level routing confidence, improving performance with minimal overhead.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.CLRecentMay 30, 2026
Confidence-Adaptive SwiGLU for Mixture-of-Experts
Shaohua Li, Xiuchao Sui, Xiaobing Sun, Yuhang Wu +3 more
The paper introduces Confidence-Adaptive SwiGLU ($κ$-SwiGLU), a novel gating mechanism for Mixture-of-Experts (MoE) models that dynamically adjusts the gate sharpness based on token-level routing conf…
View →