3 papers
cs.LG2026
Retrofitting Linear Attention into Diffusion Language Models
Jinha Kim, Younghun Roh, Jaeyeon Kim
Diffusion language models (dLLMs) offer a promising alternative to autoregressive models by accelerating inference through parallel decoding. Recent dLLMs commonly use blockwise se…
cs.LG2025
WACA-UNet: Weakness-Aware Channel Attention for Static IR Drop Prediction in Integrated Circuit Design
Youngmin Seo, Yunhyeong Kwon, Younghun Park +6
Accurate spatial prediction of power integrity issues, such as IR drop, is critical for reliable VLSI design. However, traditional simulation-based solvers are computationally expe…
cs.LG2024
Swish-T : Enhancing Swish Activation with Tanh Bias for Improved Neural Network Performance
Youngmin Seo, Jinha Kim, Unsang Park
We propose the Swish-T family, an enhancement of the existing non-monotonic activation function Swish. Swish-T is defined by adding a Tanh bias to the original Swish function. This…