4 citations · 10 across the 15 of their papers we have counts for
18 papers
Reward-guided Fine-Tuning of One-Step Generative Models via Wasserstein Gradient Flow
Hoseong Hwang, Woorim Han, Joungin Chun +2
To mitigate the time complexity of generative models, one-step generative models have recently emerged through direct mapping from noise to data in a single forward pass. However,…
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…
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…
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…
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…
Multi-Class Support Vector Machine with Differential Privacy
Jinseong Park, Yujin Choi, Jaewook Lee
With the increasing need to safeguard data privacy in machine learning models, differential privacy (DP) is one of the major frameworks to build privacy-preserving models. Support…
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…
Safeguarding Privacy of Retrieval Data against Membership Inference Attacks: Is This Query Too Close to Home?
Yujin Choi, Youngjoo Park, Junyoung Byun +2
Retrieval-augmented generation (RAG) mitigates the hallucination problem in large language models (LLMs) and has proven effective for personalized usages. However, delivering priva…
Leveraging Programmatically Generated Synthetic Data for Differentially Private Diffusion Training
Yujin Choi, Jinseong Park, Junyoung Byun +1
Programmatically generated synthetic data has been used in differential private training for classification to enhance performance without privacy leakage. However, as the syntheti…
BayesNAM: Leveraging Inconsistency for Reliable Explanations
Hoki Kim, Jinseong Park, Yujin Choi +2
Neural additive model (NAM) is a recently proposed explainable artificial intelligence (XAI) method that utilizes neural network-based architectures. Given the advantages of neural…
TimeBridge: Better Diffusion Prior Design with Bridge Models for Time Series Generation
Jinseong Park, Seungyun Lee, Woojin Jeong +2
Time series generation is widely used in real-world applications such as simulation, data augmentation, and hypothesis testing. Recently, diffusion models have emerged as the de fa…
Are Self-Attentions Effective for Time Series Forecasting?
Dongbin Kim, Jinseong Park, Jaewook Lee +1
Time series forecasting is crucial for applications across multiple domains and various scenarios. Although Transformer models have dramatically advanced the landscape of forecasti…
Fair Sampling in Diffusion Models through Switching Mechanism
Yujin Choi, Jinseong Park, Hoki Kim +2
Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer fro…
Differentially Private Sharpness-Aware Training
Jinseong Park, Hoki Kim, Yujin Choi +1
Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from sta…
Exploring the Effect of Multi-step Ascent in Sharpness-Aware Minimization
Hoki Kim, Jinseong Park, Yujin Choi +2
Recently, Sharpness-Aware Minimization (SAM) has shown state-of-the-art performance by seeking flat minima. To minimize the maximum loss within a neighborhood in the parameter spac…
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…
Comment on Transferability and Input Transformation with Additive Noise
Hoki Kim, Jinseong Park, Jaewook Lee
Adversarial attacks have verified the existence of the vulnerability of neural networks. By adding small perturbations to a benign example, adversarial attacks successfully generat…
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
Boseop Kim, HyoungSeok Kim, Sang-Woo Lee +34
GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data. Here we address some remaining issues less report…