2 citations · 2 across the 14 of their papers we have counts for
14 papers
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders
Seunghyun Lee, Byoungkwon Kim, Jaehyun Nam +2
The rapid advancement of generative models has blurred the boundary between synthetic and real imagery, creating an urgent need for reliable deepfake detection. Yet most existing a…
Trust Region Q Adjoint Matching
Yonghoon Dong, Kyungmin Lee, Changyeon Kim +2
Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-l…
RLDX-1 Technical Report
Dongyoung Kim, Huiwon Jang, Myungkyu Koo +65
While Vision-Language-Action models (VLAs) have shown remarkable progress toward human-like generalist robotic policies through the versatile intelligence (i.e. broad scene underst…
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
Kyungmin Lee, Sihyun Yu, Jinwoo Shin
Denoising generative models, such as diffusion and flow-based models, produce high-quality samples but require many denoising steps due to discretization error. Flow maps, which es…
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model
John Won, Kyungmin Lee, Huiwon Jang +2
Augmenting vision-language-action models (VLAs) with world models is promising for robotic policy learning but faces challenges in jointly predicting states and actions due to the…
Contrastive Representation Regularization for Vision-Language-Action Models
Taeyoung Kim, Jimin Lee, Myungkyu Koo +5
Vision-Language-Action (VLA) models have shown strong capabilities in robot manipulation by leveraging rich representations from pre-trained Vision-Language Models (VLMs). However,…
HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy
Myungkyu Koo, Daewon Choi, Taeyoung Kim +4
Inherently, robotic manipulation tasks are history-dependent: leveraging past context could be beneficial. However, most existing Vision-Language-Action models (VLAs) have been des…
StarFT: Robust Fine-tuning of Zero-shot Models via Spuriosity Alignment
Younghyun Kim, Jongheon Jeong, Sangkyung Kwak +3
Learning robust representations from data often requires scale, which has led to the success of recent zero-shot models such as CLIP. However, the obtained robustness can easily be…
Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance
June Suk Choi, Kyungmin Lee, Sihyun Yu +3
Recent text-to-video (T2V) models have demonstrated strong capabilities in producing high-quality, dynamic videos. To improve the visual controllability, recent works have consider…
Calibrated Multi-Preference Optimization for Aligning Diffusion Models
Kyungmin Lee, Xiaohang Li, Qifei Wang +7
Aligning text-to-image (T2I) diffusion models with preference optimization is valuable for human-annotated datasets, but the heavy cost of manual data collection limits scalability…
DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing
June Suk Choi, Kyungmin Lee, Jongheon Jeong +3
Recent advances in diffusion models have introduced a new era of text-guided image manipulation, enabling users to create realistic edited images with simple textual prompts. Howev…
DreamFlow: High-Quality Text-to-3D Generation by Approximating Probability Flow
Kyungmin Lee, Kihyuk Sohn, Jinwoo Shin
Recent progress in text-to-3D generation has been achieved through the utilization of score distillation methods: they make use of the pre-trained text-to-image (T2I) diffusion mod…
Improving Diffusion Models for Authentic Virtual Try-on in the Wild
Yisol Choi, Sangkyung Kwak, Kyungmin Lee +2
This paper considers image-based virtual try-on, which renders an image of a person wearing a curated garment, given a pair of images depicting the person and the garment, respecti…
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion Models
Kyungmin Lee, Sangkyung Kwak, Kihyuk Sohn +1
Text-to-image (T2I) diffusion models, when fine-tuned on a few personal images, can generate visuals with a high degree of consistency. However, such fine-tuned models are not robu…