Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xi Wu

Xi Wu

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

Sound×1NLP×1Crypto×1AI×1ML×1

Frequent co-authors

Yichen Gao1×
Yiqun Zhang1×
Zijing Wang1×
Yujia Li1×
Heng Guo1×
Xiaocui Yang1×

Research Timeline

2026
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack

The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits this region.

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness by correcting this arbitration bias.

Highlighted terms show continued research focus across papers

Papers

cs.SDcs.CLRecentJun 3, 2026

Beyond Text Following: Repairable Arbitration Reversals in Audio-Language Models

Yichen Gao, Yiqun Zhang, Zijing Wang, Yujia Li +6 more

The paper demonstrates that audio-language models often ignore conflicting audio evidence in favor of text, and proposes a training-free decoding rule, GACL, that significantly improves faithfulness b…

View →
cs.CRcs.AIcs.LGRecentMay 24, 2026

Furina: Fragmented Uncertainty-Driven Refusal Instability Attack

Tongxi Wu, Jian Zhang, Yang Gao

The paper challenges the assumption that LLM safety is a binary threshold, proposing that safety failures occur in an 'instability region' and introducing Furina, a transferable attack that exploits t…

View →