Research

2 papers

• 20 Jun 2026 An Empirical Study of Symmetry-Induced Parameter Sharing as an Inductive Bias in Neural Networks Kim Juhwan This study empirically investigates whether parameter sharing based on task-inherent symmetry can serve as an inductive bias in neural networks. Although standard Multi-Layer Perceptrons (MLPs) are highly expressive, they are also prone to learning unnecessary dependencies on input order or struc... →
• 20 Jun 2026 Can a Knowledge-Sharing System Survive in a Competitive Academic Environment? Lee Sihoo This paper reports on a social experiment designed to test a single hypothesis: that in a hyper-competitive academic environment, students will voluntarily share their intellectual assets if provided with the right structural infrastructure—even in the absence of any extrinsic reward. →