5 papers
Linguistics-Aware Non-Distortionary LLM Watermarking
Shinwoo Park, Hyejin Park, Hyeseon An +1
Watermarking should identify language-model output without degrading quality or limiting verification to the model provider. Multilingual deployment makes this harder because morph…
Hybrid-TTA: Continual Test-time Adaptation via Dynamic Domain Shift Detection
Hyewon Park, Hyejin Park, Jueun Ko +1
Continual Test Time Adaptation (CTTA) has emerged as a critical approach for bridging the domain gap between the controlled training environments and the real-world scenarios, enha…
Dynamic Guidance Adversarial Distillation with Enhanced Teacher Knowledge
Hyejin Park, Dongbo Min
In the realm of Adversarial Distillation (AD), strategic and precise knowledge transfer from an adversarially robust teacher model to a less robust student model is paramount. Our…
Emerging Property of Masked Token for Effective Pre-training
Hyesong Choi, Hunsang Lee, Seyoung Joung +3
Driven by the success of Masked Language Modeling (MLM), the realm of self-supervised learning for computer vision has been invigorated by the central role of Masked Image Modeling…
Salience-Based Adaptive Masking: Revisiting Token Dynamics for Enhanced Pre-training
Hyesong Choi, Hyejin Park, Kwang Moo Yi +2
In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Mod…