 LUCAS: Layered Universal Codec AvatarsComputer Vision and Pattern Recognition (CVPR), 2025 |
 Improved Training Technique for Latent Consistency ModelsInternational Conference on Learning Representations (ICLR), 2025 |
 Type-R: Automatically Retouching Typos for Text-to-Image GenerationComputer Vision and Pattern Recognition (CVPR), 2024 |
 SINE: SINgle Image Editing with Text-to-Image Diffusion ModelsComputer Vision and Pattern Recognition (CVPR), 2022 |
