Vision and Video Dynamics Lab · News
News
2026
- Paper
"Not All Prediction Targets Keep Training-Free Diffusion Guidance on the Manifold" accepted to ECCV 2026.
- Paper
"Probing Intrinsic Bias: Internal Attention Feature Analysis for Social Bias Evaluation in Diffusion Models" accepted to Neurocomputing.
- Lab
ViViD Lab officially launches at SeoulTech. Welcome!
2025
- Paper
"Temporal Smoothness-Aware Rate-Distortion Optimized 4D Gaussian Splatting" accepted to NeurIPS 2025.
2023
- Paper
"Exploring Discontinuity for Video Frame Interpolation" accepted to CVPR 2023 (Highlight, top 10%).