7 papers
DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch Attack
Hoseong Tae, Jong-Seok Lee
Flow-matching vision-language-action (VLA) models such as pi0 generate robot actions by integrating a learned denoising velocity field, and have been reported to resist adversarial…
Pooling-Based Context Modeling for Convolution-Free Deep Image Prior
Gihyun Kim, Jong-Seok Lee
Convolutional Neural Networks (CNNs) achieve strong denoising performance by exploiting spatial context from neighboring pixels. Deep Image Prior (DIP) leverages this property to r…
Dominant vs. Dominated: Concept-Level Generative Collapse in Diffusion Models
Hayeon Jeong, Jong-Seok Lee
Text-to-image diffusion models have attracted significant attention for their ability to generate diverse, high-fidelity images. However, in multi-concept generation, one concept t…
Emotional EEG Classification using Upscaled Connectivity Matrices
Chae-Won Lee, Jong-Seok Lee
In recent studies of emotional EEG classification, connectivity matrices have been successfully employed as input to convolutional neural networks (CNNs), which can effectively con…
Impact of Regularization on Calibration and Robustness: from the Representation Space Perspective
Jonghyun Park, Juyeop Kim, Jong-Seok Lee
Recent studies have shown that regularization techniques using soft labels, e.g., label smoothing, Mixup, and CutMix, not only enhance image classification accuracy but also mitiga…
SC-Pro: Training-Free Framework for Defending Unsafe Image Synthesis Attack
Junha Park, Jaehui Hwang, Ian Ryu +3
With advances in diffusion models, image generation has shown significant performance improvements. This raises concerns about the potential abuse of image generation, such as the…