7 papers
LoopUS: Recasting Pretrained LLMs into Looped Latent Refinement Models
Taekhyun Park, Yongjae Lee, Dohee Kim +1
Looped computation shows promise in improving the reasoning-oriented performance of LLMs by scaling test-time compute. However, existing approaches typically require either trainin…
ACFormer: Mitigating Non-linearity with Auto Convolutional Encoder for Time Series Forecasting
Gawon Lee, Hanbyeol Park, Minseop Kim +2
Time series forecasting (TSF) faces challenges in modeling complex intra-channel temporal dependencies and inter-channel correlations. Although recent research has highlighted the…
FEATHer: Fourier-Efficient Adaptive Temporal Hierarchy Forecaster for Time-Series Forecasting
Jaehoon Lee, Seungwoo Lee, Younghwi Kim +2
Time-series forecasting is fundamental in industrial domains like manufacturing and smart factories. As systems evolve toward automation, models must operate on edge devices (e.g.,…
IConv: Focusing on Local Variation with Channel Independent Convolution for Multivariate Time Series Forecasting
Gawon Lee, Hanbyeol Park, Minseop Kim +2
Real-world time-series data often exhibit non-stationarity, including changing trends, irregular seasonality, and residuals. In terms of changing trends, recently proposed multi-la…
Legacy Learning Strategy Based on Few-Shot Font Generation Models for Automatic Text Design in Metaverse Content
Younghwi Kim, Dohee Kim, Seok Chan Jeong +1
The metaverse consists of hardware, software, and content, among which text design plays a critical role in enhancing user immersion and usability as a content element. However, in…
Distributed Lag Transformer based on Time-Variable-Aware Learning for Explainable Multivariate Time Series Forecasting
Younghwi Kim, Dohee Kim, Joongrock Kim +1
Time series data is a key element of big data analytics, commonly found in domains such as finance, healthcare, climate forecasting, and transportation. In large scale real world s…