1

TIMING: Temporality-Aware Integrated Gradients for Time Series Explanation

Hyeongwon Jang, Changhun Kim, Eunho Yang

Mar. 20, 10998

Stable-TTS: Stable Speaker-Adaptive Text-to-Speech Synthesis via Prosody Prompting

Speaker-adaptive Text-to-Speech (TTS) synthesis has attracted considerable attention due to its broad range of applications, such as …

Wooseok Han, Minki Kang, Changhun Kim, Eunho Yang

Mar. 300, 9998

CloudFixer: Test-Time Adaptation for 3D Point Clouds via Diffusion-Guided Geometric Transformation

3D point clouds captured from real-world sensors frequently encompass noisy points due to various obstacles, such as occlusion, limited …

Hajin Shim, Changhun Kim, Eunho Yang

Mar. 290, 9998

SGEM: Test-Time Adaptation for Automatic Speech Recognition via Sequential-Level Generalized Entropy Minimization

Automatic speech recognition (ASR) models are frequently exposed to data distribution shifts in many real-world scenarios, leading to …

Changhun Kim, Joonhyung Park, Hajin Shim, Eunho Yang

Mar. 30, 7998

DeltaSHAP: Explaining Prediction Evolutions in Online Patient Monitoring with Shapley Values

Changhun Kim, Yechan Mun, Sangchul Hahn, Eunho Yang

Mar. 20, 1998

AdapTable: Test-Time Adaptation for Tabular Data via Shift-Aware Uncertainty Calibrator and Label Distribution Handler

In real-world scenarios, tabular data often suffer from distribution shifts that threaten the performance of machine learning models. …

Changhun Kim, Taewon Kim, Seungyeon Woo, June Yong Yang, Eunho Yang

Mar. 10, 1998