κ-SwiGLU adapts SiLU gate sharpness in MoE Transformers as a learnable function of router logits, reporting improved mean CORE performance on FineWeb-Edu across 8-28 layer models with negligible added parameters and small overhead.
arXiv preprint arXiv:2405.20768 , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Confidence-Adaptive SwiGLU for Mixture-of-Experts
κ-SwiGLU adapts SiLU gate sharpness in MoE Transformers as a learnable function of router logits, reporting improved mean CORE performance on FineWeb-Edu across 8-28 layer models with negligible added parameters and small overhead.