Search Results for author:
Found 2 papers, 2 papers with code
Decomposing the Neurons: Activation Sparsity via Mixture of Experts for Continual Test Time Adaptation
Continual Test-Time Adaptation (CTTA), which aims to adapt the pre-trained model to ever-evolving target domains, emerges as an important task for vision models.
DesignEdit: Multi-Layered Latent Decomposition and Fusion for Unified & Accurate Image Editing
Second, we propose an instruction-guided latent fusion that pastes the multi-layered latent representations onto a canvas latent.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
