2 papers
cs.LG2026
Confidence-Adaptive SwiGLU for Mixture-of-Experts
Shaohua Li, Xiuchao Sui, Xiaobing Sun +4
SwiGLU has become a standard gated activation in modern Transformer MLPs, yet its gate sharpness -- the smoothness and selectivity of the gating function -- is typically fixed thro…
cs.CL2026
Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models
Xiaobing Sun, Perry Lam, Shaohua Li +4
Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent semantic representations and generation-time reasoning, enabling them to recover obf…