11 papers
Not Every Time and Frequency Need to Be Forgotten in Diffusion Unlearning
Jinseong Park, Mijung Park
Data unlearning aims to remove the influence of specific training samples from a trained model. In fine-tuning methods, data unlearning relies primarily on loss maximization over f…
Co-occurring associated retained concepts in Diffusion Unlearning
Miso Kim, Georu Lee, Yunji Kim +3
Unlearning has emerged as a key technique to mitigate harmful content generation in diffusion models. However, existing methods often remove not only the target concept, but also b…
Stability Analysis of Sharpness-Aware Minimization
Hoki Kim, Jinseong Park, Yujin Choi +1
Sharpness-aware minimization (SAM) is a training method that seeks to find flat minima in deep learning, resulting in state-of-the-art performance across various domains. Instead o…
Machine Unlearning for Masked Diffusion Language Models
Georu Lee, Seungwon Jeong, Hoki Kim +2
Recent masked diffusion language models (MDLMs), such as LLaDA and Dream, have achieved performance comparable to autoregressive large language models. Unlike autoregressive models…
Dementia-R1: Reinforced Pretraining and Reasoning from Unstructured Clinical Notes for Real-World Dementia Prognosis
Choonghan Kim, Hyunmin Hwang, Hangeol Chang +4
While Large Language Models (LLMs) have shown strong performance on clinical text understanding, they struggle with longitudinal prediction tasks such as dementia prognosis, which…
Unlearning for One-Step Generative Models via Unbalanced Optimal Transport
Hyundo Choi, Junhyeong An, Jinseong Park +1
Recent advances in one-step generative frameworks, such as flow map models, have significantly improved the efficiency of image generation by learning direct noise-to-data mappings…