5 papers
Early Decisions Matter: Proximity Bias and Initial Trajectory Shaping in Non-Autoregressive Diffusion Language Models
Jiyeon Kim, Sungik Choi, Yongrae Jo +2
Diffusion-based language models (dLLMs) have emerged as a promising alternative to autoregressive language models, offering the potential for parallel token generation and bidirect…
HFI: A unified framework for training-free detection and implicit watermarking of latent diffusion model generated images
Sungik Choi, Hankook Lee, Jaehoon Lee +3
Dramatic advances in the quality of the latent diffusion models (LDMs) also led to the malicious use of AI-generated images. While current AI-generated image detection methods assu…
Training-free Detection of AI-generated images via Cropping Robustness
Sungik Choi, Hankook Lee, Moontae Lee
AI-generated image detection has become crucial with the rapid advancement of vision-generative models. Instead of training detectors tailored to specific datasets, we study a trai…
Diffusion based Semantic Outlier Generation via Nuisance Awareness for Out-of-Distribution Detection
Suhee Yoon, Sanghyu Yoon, Ye Seul Sim +5
Out-of-distribution (OOD) detection, which determines whether a given sample is part of the in-distribution (ID), has recently shown promising results through training with synthet…
Partial-Multivariate Model for Forecasting
Jaehoon Lee, Hankook Lee, Sungik Choi +2
When solving forecasting problems including multiple time-series features, existing approaches often fall into two extreme categories, depending on whether to utilize inter-feature…