Hsuan-Tien Lin

Complementary-label learning valuation breaks at low noise rates, but a new cost-margin formulation unlocks near-perfect noise detection and performance gains.

Self-Output Fine-Tuning (SOFT) effectively curbs the butterfly effect in weather forecasting, transforming initial prediction errors into a manageable calibration process.

Diffusion models aren't just good for generating synthetic data for robust training; their internal representations can be directly leveraged to boost adversarial robustness and disentangle features.