activity
20232026
most citedActivation by Interval-wise Dropout: A Simple Way to Prevent Neural Networks from Plasticity Loss

2 citations · 3 across the 5 of their papers we have counts for

collaborators
Showing 2026Show all

2 papers · 1 filter

cs.LG2026

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

Isaac Han, Sangyeon Park, Seungwon Oh +3

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…

cs.MA2026

Prism: Spectral Parameter Sharing for Multi-Agent Reinforcement Learning

Kyungbeom Kim, Seungwon Oh, Kyung-Joong Kim

Parameter sharing is a key strategy in multi-agent reinforcement learning (MARL) for improving scalability, yet conventional fully shared architectures often collapse into homogene…