3 papers
cs.CV2026
T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models
Jaehyuk Jang, Minseok Seo, Minseok Seo. Seungju Cho +3
Vision-language models (VLMs) achieve strong zero-shot recognition, but they remain highly vulnerable to adversarial perturbations. Recent test-time adaptations improve robustness…
cs.SD2026
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…
cs.SD2026
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…