Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
LoRA Training Provably Converges to a Low-Rank Global Minimum or It Fails Loudly (But it Probably Won't Fail)
Junsu Kim, Jaeyeon Kim, Ernest K. Ryu
Low-rank adaptation (LoRA) has become a standard approach for fine-tuning large foundation models. However, our theoretical understanding of LoRA remains limited as prior analyses…
cs.LG2024
Gradient-free Decoder Inversion in Latent Diffusion Models
Seongmin Hong, Suh Yoon Jeon, Kyeonghyun Lee +2
In latent diffusion models (LDMs), denoising diffusion process efficiently takes place on latent space whose dimension is lower than that of pixel space. Decoder is typically used…