 TRACE: Temporally Reliable Anatomically-Conditioned 3D CT Generation with Enhanced EfficiencyInternational Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025 |
 ViSAGe: Video-to-Spatial Audio GenerationInternational Conference on Learning Representations (ICLR), 2025 |
 FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian VelocityComputer Vision and Pattern Recognition (CVPR), 2025 |
 FADE: Frequency-Aware Diffusion Model Factorization for Video EditingComputer Vision and Pattern Recognition (CVPR), 2025 |
 Diff2Flow: Training Flow Matching Models via Diffusion Model AlignmentComputer Vision and Pattern Recognition (CVPR), 2025 |
