9 papers
Safety in Batches? Understanding and Mitigating Safety Failures in Batch Prompting
Kihyun Kim, Hee-Seon Kim, Wonjun Lee +1
Batch prompting is a practical inference strategy for large language models, but its safety implications remain underexplored. We show that the success of batch prompting for utili…
Constraining to Generalize: Subspace Tuning for Few-shot Generalization of Audio-Language Models
Jaehyuk Jang, Kangwook Ko, Wonjun Lee +1
Few-shot adaptation of pretrained Audio--Language Models (ALMs) often improves seen-class performance at the cost of unseen-class generalization, leading to the base-to-new trade-o…
Jailbreak to Protect: Buffering and Reinforcing via Temporary Jailbreaking for Safe Fine-Tuning in Large Language Models
Seokil Ham, Jaehyuk Jang, Wonjun Lee +1
Fine-tuning-as-a-Service (FaaS) enables personalization of large language models (LLMs), but it can weaken safety-alignment under harmful fine-tuning attacks. Recent work has shown…
Generalizable Prompt Tuning for Audio-Language Models via Semantic Expansion
Jaehyuk Jang, Wonjun Lee, Kangwook Ko +1
Prompt tuning has achieved remarkable progress in vision-language models (VLMs) and is recently being adopted for audio-language models (ALMs). However, its generalization ability…
Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation
Minseok Seo, Wonjun Lee, Jaehyuk Jang +1
Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches…
SELFI: Selective Fusion of Identity for Generalizable Deepfake Detection
Younghun Kim, Minsuk Jang, Myung-Joon Kwon +2
Face identity provides a powerful signal for deepfake detection. Prior studies show that even when not explicitly modeled, classifiers often learn identity features implicitly. Thi…