4 papers
When does training on downscaled images yield the same gradients?
Seunghyun Ji
Diffusion transformers deliver strong image generation, but their training cost grows superlinearly with resolution. Recent work justifies training or sampling at reduced resolutio…
Ortho-Hydra: Orthogonalized Experts for DiT LoRA
Seunghyun Ji
LoRA fine-tuning of diffusion transformers (DiT) on multi-style data suffers from \emph{style bleed}: a single low-rank residual cannot represent several distinct artist fingerprin…
Confidence Regularized Masked Language Modeling using Text Length
Seunghyun Ji, Soowon Lee
Masked language modeling is a widely used method for learning language representations, where the model predicts a randomly masked word in each input. However, this approach typica…
Robust Guidance for Unsupervised Data Selection: Capturing Perplexing Named Entities for Domain-Specific Machine Translation
Seunghyun Ji, Hagai Raja Sinulingga, Darongsae Kwon
Low-resourced data presents a significant challenge for neural machine translation. In most cases, the low-resourced environment is caused by high costs due to the need for domain…