← Search

Seungwon Oh

2 accepted papers

2026

FIRE: Frobenius-Isometry Reinitialization for Balancing the Stability–Plasticity Tradeoff

ICLR 2026oral

Deep neural networks trained on nonstationary data must balance stability (i.e., retaining prior knowledge) and plasticity (i.e., adapting to new tasks). Standard reinitialization methods, which reinitialize weights toward their original values, are widely used but difficult to tune: conservative re…

Cited by 0SourceScholar
2025

Activation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

ICML 2025poster

Plasticity loss, a critical challenge in neural network training, limits a model's ability to adapt to new tasks or shifts in data distribution. While widely used techniques like L2 regularization and Layer Normalization have proven effective in mitigating this issue, Dropout remains notably ineffec…

Cited by 1SourcePDFScholar