• Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs (Main)

H.Cho, S.Yoo, Jaehyuk Jang, Changick Kim† and J. Chung† († These two authors are co-corresponding authors)

• Where Identity Lives: Localized, Retain-Free Identity Unlearning in Multimodal Large Language Models (Findings)

Kangwook Ko*, Jaehyuk Jang*, Wonjun Lee*, Hee-Seon Kim and Changick Kim (* These three authors contributed equally)

• AIM: Anchor Identity Features, then Match for Multimodal Large Language Model Unlearning (Findings)

Wonjun Lee*, Jaehyuk Jang*, Kangwook Ko*, Hee-Seon Kim and Changick Kim (* These three authors contributed equally)

• Constraining to Generalize: Subspace Tuning for Few-shot Generalization of Audio-Language Models (Findings)

Jaehyuk Jang, Kangwook Ko, Wonjun Lee and Changick Kim

• MATE: Mobile Agent Trustworthy Execution for Safe and Efficient Mobile Control (Findings)

Minsuk Jang*, Hee-Seon Kim*, H. Yu*, and Changick Kim (* These three authors contributed equally)