21 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Daegu Gyeongbuk Institute of Science and TechnologyKR1 paper
- Kakao Enterprise (South Korea)KR1 paper
- Korea Advanced Institute of Science and TechnologyKR1 paper
- Korea Kacoh (South Korea)KR1 paper
- National Laboratory of the RockiesUS1 paper
- Seoul National UniversityKR1 paper
- University of Colorado BoulderUS1 paper
4 papers
ModSandbox: Facilitating Online Community Moderation Through Error Prediction and Improvement of Automated Rules
Jean Y. Song, Sangwook Lee, Jisoo Lee +2
Despite the common use of rule-based tools for online content moderation, human moderators still spend a lot of time monitoring them to ensure that they work as intended. Based on…
Accelerating RNN Transducer Inference via One-Step Constrained Beam Search
Juntae Kim, Yoonhan Lee
We propose a one-step constrained (OSC) beam search to accelerate recurrent neural network (RNN) transducer (RNN-T) inference. The original RNN-T beam search has a while-loop leadi…
Signal-Anticipation in Local Voltage Control in Distribution Systems
Zhiyuan Liu, Seungil You, Xinyang Zhou +2
We consider the signal-anticipating behavior in local Volt/Var control for distribution systems. Such a behavior makes interaction among the nodes a game. We characterize Nash equi…
Maximum Causal Tsallis Entropy Imitation Learning
Kyungjae Lee, Sungjoon Choi, Songhwai Oh
In this paper, we propose a novel maximum causal Tsallis entropy (MCTE) framework for imitation learning which can efficiently learn a sparse multi-modal policy distribution from d…