10 papers
Bootstrapping Video Interaction Generation with Synthetic State Transitions
Jiho Jang, Jinyoung Kim, Nojun Kwak +2
While recent video generative models can synthesize high-fidelity videos, they struggle to portray plausible physical interactions and the resulting state transitions, a critical b…
Multi-dimensional Preference Alignment by Conditioning Reward Itself
Jiho Jang, Jinyoung Kim, Kyungjune Baek +1
Reinforcement Learning from Human Feedback has emerged as a standard for aligning diffusion models. However, we identify a fundamental limitation in the standard DPO formulation be…
Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting
Hyeongmin Lee, Kyungjune Baek
Dynamic 4D Gaussian Splatting (4DGS) effectively extends the high-speed rendering capabilities of 3D Gaussian Splatting (3DGS) to represent volumetric videos. However, the large nu…
Rethinking Direct Preference Optimization in Diffusion Models
Junyong Kang, Seohyun Lim, Kyungjune Baek +1
Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optim…
Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments
Soonwoo Kwon, Jin-Young Kim, Hyojun Go +1
We present a novel study on enhancing the capability of preserving the content in world models, focusing on a property we term World Stability. Recent diffusion-based generative mo…
MomentMix Augmentation with Length-Aware DETR for Temporally Robust Moment Retrieval
Seojeong Park, Jiho Choi, Kyungjune Baek +1
Video Moment Retrieval (MR) aims to localize moments within a video based on a given natural language query. Given the prevalent use of platforms like YouTube for information retri…
TWLV-I: Analysis and Insights from Holistic Evaluation on Video Foundation Models
Hyeongmin Lee, Jin-Young Kim, Kyungjune Baek +18
In this work, we discuss evaluating video foundation models in a fair and robust manner. Unlike language or image foundation models, many video foundation models are evaluated with…
Commonality in Natural Images Rescues GANs: Pretraining GANs with Generic and Privacy-free Synthetic Data
Kyungjune Baek, Hyunjung Shim
Transfer learning for GANs successfully improves generation performance under low-shot regimes. However, existing studies show that the pretrained model using a single benchmark da…
Rethinking the Truly Unsupervised Image-to-Image Translation
Kyungjune Baek, Yunjey Choi, Youngjung Uh +2
Every recent image-to-image translation model inherently requires either image-level (i.e. input-output pairs) or set-level (i.e. domain labels) supervision. However, even set-leve…
Editable Generative Adversarial Networks: Generating and Editing Faces Simultaneously
Kyungjune Baek, Duhyeon Bang, Hyunjung Shim
We propose a novel framework for simultaneously generating and manipulating the face images with desired attributes. While the state-of-the-art attribute editing technique has achi…