9 papers
AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking
Jungkyu Kim, Taeyoung Park, Kibok Lee
Score-based diffusion models have emerged as prominent deep generative models; however, their application to tabular data remains challenging because their backbones assume fully s…
Dataset-Driven Channel Masks in Transformers for Multivariate Time Series
Seunghan Lee, Taeyoung Park, Kibok Lee
Recent advancements in foundation models have been successfully extended to the time series (TS) domain, facilitated by the emergence of large-scale TS datasets. However, previous…
Improving Calibration in Test-Time Prompt Tuning for Vision-Language Models via Data-Free Flatness-Aware Prompt Pretraining
Hyeonseo Jang, Jaebyeong Jeon, Joong-Won Hwang +1
Test-time prompt tuning (TPT) has emerged as a promising technique for enhancing the adaptability of vision-language models by optimizing textual prompts using unlabeled test data.…
When and Where to Reset Matters for Long-Term Test-Time Adaptation
Taejun Lim, Joong-Won Hwang, Kibok Lee
When continual test-time adaptation (TTA) persists over the long term, errors accumulate in the model and further cause it to predict only a few classes for all inputs, a phenomeno…
Soft Contrastive Learning for Time Series
Seunghan Lee, Taeyoung Park, Kibok Lee
Contrastive learning has shown to be effective to learn representations from time series in a self-supervised way. However, contrasting similar time series instances or values from…
Channel Normalization for Time Series Channel Identification
Seunghan Lee, Taeyoung Park, Kibok Lee
Channel identifiability (CID) refers to the ability to distinguish between individual channels in time series (TS) modeling. The absence of CID often results in producing identical…