7 papers
Latent-Mark: An Audio Watermark Robust to Neural Codec Compression
Yen-Shan Chen, Shih-Yu Lai, Ying-Jung Tsou +5
While existing audio watermarking techniques have achieved strong robustness against traditional digital signal processing (DSP) attacks, they remain vulnerable to neural compressi…
MAIGO: Mitigating Lost-in-Conversation with History-Cleaned On-Policy Self-Distillation
Haoyu Zheng, Yun Zhu, Shu Yuan +5
Large language models often solve tasks from a fully specified prompt but degrade when the same requirements unfold over multiple turns, known as the lost-in-conversation (LiC) gap…
Pseudo2Real: Task Arithmetic for Pseudo-Label Correction in Automatic Speech Recognition
Yi-Cheng Lin, Yu-Hsuan Li Liang, Hsuan Su +4
Robust ASR under domain shift is crucial because real-world systems encounter unseen accents and domains with limited labeled data. Although pseudo-labeling offers a practical work…
ALICE: A Multifaceted Evaluation Framework of Large Audio-Language Models' In-Context Learning Ability
Yen-Ting Piao, Jay Chiehen Liao, Wei-Tang Chien +5
While Large Audio-Language Models (LALMs) have been shown to exhibit degraded instruction-following capabilities, their ability to infer task patterns from in-context examples unde…
Safeguard Fine-Tuned LLMs Through Pre- and Post-Tuning Model Merging
Hua Farn, Hsuan Su, Shachi H Kumar +3
Fine-tuning large language models (LLMs) for downstream tasks often leads to catastrophic forgetting, notably degrading the safety of originally aligned models. While some existing…
Jailbreaking with Universal Multi-Prompts
Yu-Ling Hsu, Hsuan Su, Shang-Tse Chen
Large language models (LLMs) have seen rapid development in recent years, revolutionizing various applications and significantly enhancing convenience and productivity. However, al…