Author

Daehwa Ko

h-index 0 View on Semantic Scholar

We have 1 of 4 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.

Preprint Aug 2026

TESLA: Taylor Expansion of Sinusoidal Learnable Activations

TESLA, an activation defined as a learnable combination of sine and cosine terms, enabling explicit control over polynomial degree and selective amplification of high-order components is proposed, indicating that activation-level degree control transfers to more general vision workloads.

Daehwa Ko, Jae-Hwan Kim, Seunghyun Ham et al. · 0 citations