3 papers
cs.CV2025
Rethinking Direct Preference Optimization in Diffusion Models
Junyong Kang, Seohyun Lim, Kyungjune Baek +1
Aligning text-to-image (T2I) diffusion models with human preferences has emerged as a critical research challenge. While recent advances in this area have extended preference optim…
cs.CV2024
Scribble-Guided Diffusion for Training-free Text-to-Image Generation
Seonho Lee, Jiho Choi, Seohyun Lim +2
Recent advancements in text-to-image diffusion models have demonstrated remarkable success, yet they often struggle to fully capture the user's intent. Existing approaches using te…
cs.CV2024
Memory-Efficient Fine-Tuning for Quantized Diffusion Model
Hyogon Ryu, Seohyun Lim, Hyunjung Shim
The emergence of billion-parameter diffusion models such as Stable Diffusion XL, Imagen, and DALL-E 3 has significantly propelled the domain of generative AI. However, their large-…