most citedAccelerating Multi-Model Inference by Merging DNNs of Different Weights

2 citations · 4 across the 2 of their papers we have counts for

collaborators

5 papers

cs.LG20202 cited

Accelerating Multi-Model Inference by Merging DNNs of Different Weights

Joo Seong Jeong, Soojeong Kim, Gyeong-In Yu +2

Standardized DNN models that have been proved to perform well on machine learning tasks are widely used and often adopted as-is to solve downstream tasks, forming the transfer lear…

cs.LG20202 cited

Hippo: Taming Hyper-parameter Optimization of Deep Learning with Stage Trees

Ahnjae Shin, Do Yoon Kim, Joo Seong Jeong +1

Hyper-parameter optimization is crucial for pushing the accuracy of a deep learning model to its limits. A hyper-parameter optimization job, referred to as a study, involves numero…

cs.PL2018

JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative Programs

Eunji Jeong, Sungwoo Cho, Gyeong-In Yu +3

The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the requirement of quickly executing large computations, but also to supp…

cs.LG2018

Improving the Expressiveness of Deep Learning Frameworks with Recursion

Eunji Jeong, Joo Seong Jeong, Soojeong Kim +2

Recursive neural networks have widely been used by researchers to handle applications with recursively or hierarchically structured data. However, embedded control flow deep learni…

cond-mat.supr-con2018

Coexistence of Intrinsic Superconductivity and Topological Insulator State in Monoclinic Phase WS2

Yuqiang Fang, Jie Pan, Dongqin Zhang +14

Recently, intriguing phenomena of superconductivity, type-II Weyl semimetal or quantum spin Hall states were discovered in metastable 1T'-type VIB-group transition metal dichalcoge…