NaHyeon Park

2 accepted papers

2026

Directional Textual Inversion for Personalized Text-to-Image Generation

Kunhee Kim, NaHyeon Park, Kibeom Hong, Hyunjung Shim

ICLR 2026poster

Textual Inversion (TI) is an efficient approach to text‑to‑image personalization but often fails on complex prompts. We trace these failures to embedding norm inflation: learned tokens drift to out‑of‑distribution magnitudes, degrading prompt conditioning in pre‑norm Transformers. Empirically, we sh…

Cited by 0 Source ↗Scholar ↗

2025

DGQ: Distribution-Aware Group Quantization for Text-to-Image Diffusion Models

Hyogon Ryu, NaHyeon Park, Hyunjung Shim

ICLR 2025poster

Despite the widespread use of text-to-image diffusion models across various tasks, their computational and memory demands limit practical applications. To mitigate this issue, quantization of diffusion models has been explored. It reduces memory usage and computational costs by compressing weights…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗