3 papers
cs.CV2026
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…
cs.LG2026
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…
cs.CL2025
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…