← Search

Joungho Kim

2 accepted papers

2023

DevFormer: A Symmetric Transformer for Context-Aware Device Placement

ICML 2023poster

In this paper, we present DevFormer, a novel transformer-based architecture for addressing the complex and computationally demanding problem of hardware design optimization. Despite the demonstrated efficacy of transformers in domains including natural language processing and computer vision, their…

Cited by 21SourcePDFScholar
2021

Learning Collaborative Policies to Solve NP-hard Routing Problems

NeurIPS 2021poster

Recently, deep reinforcement learning (DRL) frameworks have shown potential for solving NP-hard routing problems such as the traveling salesman problem (TSP) without problem-specific expert knowledge. Although DRL can be used to solve complex problems, DRL frameworks still struggle to compete with s…