Search Results for author: Seokil Ham

Found 2 papers, 1 papers with code

Diffusion Model Patching via Mixture-of-Prompts

no code implementations28 May 2024 Seokil Ham, Sangmin Woo, Jin-Young Kim, Hyojun Go, Byeongjun Park, Changick Kim

We present Diffusion Model Patching (DMP), a simple method to boost the performance of pre-trained diffusion models that have already reached convergence, with a negligible increase in parameters.

Denoising

Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts

1 code implementation14 Mar 2024 Byeongjun Park, Hyojun Go, Jin-Young Kim, Sangmin Woo, Seokil Ham, Changick Kim

To achieve this, we employ a sparse mixture-of-experts within each transformer block to utilize semantic information and facilitate handling conflicts in tasks through parameter isolation.

Denoising Multi-Task Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.