MC

Moonseok Choi

0000-0002-1566-2731

cs.AIcs.CVcs.LGcs.IRstat.ML

On Valency

published · living versions

W_y34taueh·v1 · currentpublished

SKIM: Pruning Large Language Model Agents via Selective Knowledge Informed Masking

with Jongwon Jeong, Minki Kang, Giung Nam, Juho Lee

1 version

Preprints & journals

6 papers in the corpus · 2022–2024

Safety Alignment Backfires: Preventing the Re-emergence of Suppressed Concepts in Fine-tuned Text-to-Image Diffusion Models2412.00357v1 · Sanghyun Kim, Moonseok Choi, Jinwoo Shin et al.2024 · 0 citationsarXiv

A Simple Early Exiting Framework for Accelerated Sampling in Diffusion Models2408.05927v1 · Taehong Moon, Moonseok Choi, EungGu Yun et al.2024 · 1 citationarXiv

Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion2407.21032v1 · Sanghyun Kim, Seohyeon Jung, Balhae Kim et al.2024 · 2 citationsarXiv

Towards Safe Self-Distillation of Internet-Scale Text-to-Image Diffusion Models2307.05977v1 · Sanghyun Kim, Seohyeon Jung, Balhae Kim et al.2023 · 6 citationsarXiv

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning2305.14852v2 · Moonseok Choi, Hyungi Lee, Giung Nam et al.2023 · 0 citationsarXiv

Equal Experience in Recommender Systems2210.05936v1 · Jaewoong Cho, Moonseok Choi, Changho Suh2022 · 1 citationarXiv

Career total: 12 works. 6 are in this corpus.

Profile built from the corpus for this byline.

Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.