Sungrack Yun

Qualcomm (United Kingdom) — United Kingdom

Computer Science · Physical Sciences

10h-index321citations56works0.12yr avg
OpenAlex↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Music and Audio Processing(18), Speech and Audio Processing(17), Speech Recognition and Synthesis(15), Domain Adaptation and Few-Shot Learning(10), Multimodal Machine Learning Applications(7)

Publications56 total

Steering Guidance for Personalized Text-to-Image Diffusion Models
arXiv (Cornell University)·2025Open Access
Memory-Efficient Personalization of Text-to-Image Diffusion Models via Selective Optimization Strategies
arXiv (Cornell University)·2025Open Access
From Wardrobe to Canvas: Wardrobe Polyptych LoRA for Part-level Controllable Human Image Generation
arXiv (Cornell University)·2025Open Access
MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans
arXiv (Cornell University)·2025Open Access
Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning
2025
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
arXiv (Cornell University)·2024Open Access
FedHide: Federated Learning by Hiding in the Neighbors
arXiv (Cornell University)·2024Open Access
Feature Diversification and Adaptation for Federated Domain Generalization
arXiv (Cornell University)·2024Open Access
Balanced Learning for Multi-Domain Long-Tailed Speaker Recognition
2024· 1 cited
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
2024
Few-Shot Common Action Localization via Cross-Attentional Fusion of Context and Temporal Dynamics
2023· 3 cited
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
2023· 12 cited
Multi-Scale Temporal Feature Fusion for Few-Shot Action Recognition
2023· 1 cited
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
arXiv (Cornell University)·2023· 1 citedOpen Access
Neural Transformation Network to Generate Diverse Views for Contrastive Learning
2023· 3 cited
Progressive Random Convolutions for Single Domain Generalization
2023· 46 cited
Progressive Random Convolutions for Single Domain Generalization
arXiv (Cornell University)·2023· 1 citedOpen Access
Domain Agnostic Few-shot Learning for Speaker Verification
Interspeech 2022·2022· 4 cited
Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypes
arXiv (Cornell University)·2022· 2 citedOpen Access
Domain Agnostic Few-shot Learning for Speaker Verification
arXiv (Cornell University)·2022Open Access
page 1 of 3Next →

Frequent Co-authors

Chang D. Yoo(12), Hyunsin Park(12), Hyung Woo Park(12), Janghoon Cho(11), Seung-Han Yang(9), Kyuwoong Hwang(8), Seokeon Choi(7), Simyung Chang(7), Debasmit Das(6), Jungyun Eum(6), Jun-Tae Lee(5), Sungha Choi(4), Mihir Jain(4), Hossein Hosseini(4), Christos Louizos(4), Joseph B. Soriaga(4), Max Welling(4), Sungwoong Kim(4), Sunghyun Park(3), Jaegul Choo(3)