DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation

SeiT++: Masked Token Modeling Improves Storage-efficient Training

Memory-Efficient Fine-Tuning for Quantized Diffusion Model

Learning from Spatio-temporal Correlation for Semi-Supervised LiDAR Semantic Segmentation

Locally Conditioned GANs: Self-supervised Local Patch Representation Learning for Conditional Generation

Preventing Image Hallucination in Text-to-Image Generation through Factual Image Retrieval

Adapting Low-Dose CT Denoisers for Texture Preservation using Zero-Shot Local Noise-level Matching

Self-Supervised Vision Transformers Are Efficient Segmentation Learners for Imperfect Labels

Precision matters: Precision-aware ensemble for weakly supervised semantic segmentation

Local Expert Diffusion Models for Efficient Training in Denoising Diffusion Probabilistic Models