Author

Kai Xu

h-index 6 View on Semantic Scholar

We have 1 of 25 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Jul 2026

Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers

Ablations show that softmax approximation dominates the error budget and CKKS arithmetic noise is negligible in the authors' setting, suggesting that SNLP is complementary to block-level FHE-friendly operator design rather than a replacement for it.

Ligong Han, Kai Xu, Hao Wang et al. · arXiv.org · 0 citations