Bosun Hwang — accepted AI-conference papers

2025

From Theory to Practice: Rethinking Green and Martin Kernels for Unleashing Graph Transformers

Yoon Hyeok Lee, Jaemin Park, Taejin Paik, Doyun Kim, Bosun Hwang

ICML 2025poster

Graph Transformers (GTs) have emerged as a powerful alternative to message-passing neural networks, yet their performance heavily depends on effectively embedding structural inductive biases. In this work, we introduce novel structural encodings (SEs) grounded in a rigorous analysis of random walks…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Prevalence of Negative Transfer in Continual Reinforcement Learning: Analyses and a Simple Baseline

Hongjoon Ahn, Jinu Hyeon, Youngmin Oh, Bosun Hwang, Taesup Moon

ICLR 2025poster

We argue that the negative transfer problem occurring when the new task to learn arrives is an important problem that needs not be overlooked when developing effective Continual Reinforcement Learning (CRL) algorithms. Through comprehensive experimental validation, we demonstrate that such issue fre…

Cited by 1 Source ↗PDF ↗Scholar ↗