◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Soobin Um

8 papers hereh-index 556 citations12 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • first author3
  • middle author4
  • last author1

Across the 8 of 8 papers where every author was matched, so the position is known.

fields
  • cs.CV4
  • cs.LG2
  • cs.GR1
  • physics.optics1

identity via Semantic Scholar / OpenAlex

activity
20242026
collaborators
Showing cs.CVShow all

4 papers · 1 filter

cs.CV2026

Self-Improving Diffusion Classifiers with Minority Preference Optimization

Hyunsoo Kim, Jungmyung Wi, Soobin Um +2

Prior studies have demonstrated that diffusion classifiers achieve robust zero-shot classification performance. However, their effectiveness is strongly tied to the pretraining dat…

cs.CV2026

MotionCFG: Boosting Motion Dynamics via Stochastic Concept Perturbation

Byungjun Kim, Soobin Um, Jong Chul Ye

Despite recent advances in Text-to-Video (T2V) synthesis, generating high-fidelity and dynamic motion remains a significant challenge. Existing methods primarily rely on Classifier…

cs.CV2025

Minority-Focused Text-to-Image Generation via Prompt Optimization

Soobin Um, Jong Chul Ye

We investigate the generation of minority samples using pretrained text-to-image (T2I) latent diffusion models. Minority instances, in the context of T2I generation, can be defined…

cs.CV2024

Self-Guided Generation of Minority Samples Using Diffusion Models

Soobin Um, Jong Chul Ye

We present a novel approach for generating minority samples that live on low-density regions of a data manifold. Our framework is built upon diffusion models, leveraging the princi…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.