collaborators

5 papers

cs.LG2026

Consolidator: Learning Persistent Routed Memory Across Context Boundaries

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

Copying short-term memory (STM) into a slower store can preserve state across a context boundary, but persistence alone does not ensure that the retained state influences subsequen…

cs.LG2026

Phasor Attention: Mean Root Square Normalization for Phase Manifold Preservation

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

While Root Mean Square Normalization has become the de facto standard for accelerating modern sequence models, its reliance on the quadratic accumulation of independent scalars ($\…

cs.LG2026

Z-Plane Neural Networks: Bounded Geometric Activation Replaces ReLU and LayerNorm

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

Modern deep neural networks rely on Euclidean scalar activations (e.g., ReLU) and global normalization techniques (e.g., LayerNorm) to prevent gradient instability in deep architec…

cs.LG2026

Phasor Memory Networks: Stable Backpropagation Through Time for Scalable Explicit Memory

Sungwoo Goo, Hwi-yeol Yun, Sangkeun Jung

For over a decade, explicit memory architectures like the Neural Turing Machine have remained theoretically appealing yet practically intractable for language modeling due to catas…

q-bio.QM2025

CaliciBoost: Performance-Driven Evaluation of Molecular Representations for Caco-2 Permeability Prediction

Huong Van Le, Weibin Ren, Junhong Kim +8

Caco-2 permeability serves as a critical in vitro indicator for predicting the oral absorption of drug candidates during early-stage drug discovery. To enhance the accuracy and eff…