Yiyang Zhang
2 indexed papers
Recent (6 mo)
2With code
0Influential cites
0Benchmarked
0Publications per year
226
Top categories
Sound×1AI×1Crypto×1ML×1
Frequent co-authors
Research Timeline
2026
Stealthy and Adjustable Text-Guided Backdoor Attacks on Multimodal Pretrained Models
The paper proposes a novel Text-Guided Backdoor (TGB) attack that uses common words in text descriptions as stealthy triggers for multimodal models, enhancing practicality and controllability.
MOSS-Audio Technical Report
MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.
Highlighted terms show continued research focus across papers
Papers
cs.SDcs.AIRecentJun 1, 2026
MOSS-Audio Technical Report
Chen Yang, Chufan Yu, Hanfu Chen, Jie Zhu +21 more
MOSS-Audio is a unified audio-language model designed for comprehensive understanding of speech, environmental sounds, and music, achieving strong performance across various audio-grounded tasks.
View →
cs.CRcs.LGRecentApr 7, 2026