Author

Ke-Han Wang

2 papers indexed here

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.

Preprint Aug 2026

Role-Decoupled Attention Residuals: Separating Matching and Content Retrieval Across Depth

Role-Decoupled Attention Residuals (RD-AttnRes), a minimal extension that shares one depth route between queries and keys while learning an independent value route over the same residual sources, is introduced and suggests that, within the evaluated training regime, attention matching and content retrieval benefit from...

Ke-Han Wang · 0 citations

#artificial intelligence Jun 2026

HAARES Half-Split Residual Basis Routing for Deep Transformers

Cost analysis shows that the method is FLOP-light but not wall-clock-free: it adds memory and routing overhead, yet its relative arithmetic cost is amortized as width grows and earlier convergence can reduce time-to-target.

Ke-Han Wang · arXiv.org · 0 citations