17 citations · 19 across the 8 of their papers we have counts for
5 papers · 1 filter
SteeringTTA: Guiding Diffusion Trajectories for Robust Test-Time-Adaptation
Jihyun Yu, Yoojin Oh, Wonho Bae +2
Test-time adaptation (TTA) aims to correct performance degradation of deep models under distribution shifts by updating models or inputs using unlabeled test data. Input-only diffu…
Advancing Jailbreak Strategies: A Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses
Mohamed Ahmed, Mohamed Abdelmouty, Mingyu Kim +3
The advancement of Pre-Trained Language Models (PTLMs) and Large Language Models (LLMs) has led to their widespread adoption across diverse applications. Despite their success, the…
Bayesian Principles Improve Prompt Learning In Vision-Language Models
Mingyu Kim, Jongwoo Ko, Mijung Park
Prompt learning is a popular fine-tuning method for vision-language models due to its efficiency. It requires a small number of additional learnable parameters while significantly…
Amplifying Minority Voices: AI-Mediated Devil's Advocate System for Inclusive Group Decision-Making
Soohwan Lee, Mingyu Kim, Seoyeong Hwang +2
Group decision-making often benefits from diverse perspectives, yet power imbalances and social influence can stifle minority opinions and compromise outcomes. This prequel introdu…
Training-Free Safe Denoisers for Safe Use of Diffusion Models
Mingyu Kim, Dongjun Kim, Amman Yusuf +2
There is growing concern over the safety of powerful diffusion models (DMs), as they are often misused to produce inappropriate, not-safe-for-work (NSFW) content or generate copyri…