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

Linxin Song

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×1Crypto×1AI×1

Frequent co-authors

Jieyu Zhao2×
Meihua Dang1×
Honghua Zhang1×
Guy Van den Broeck1×
Stefano Ermon1×
Xuwei Ding1×

Research Timeline

2026
The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high attack success rates even for safety-aligned models.

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed and performance compared to existing approaches.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentJun 1, 2026

Mitigating Bias in Locally Constrained Decoding via Tractable Proposals

Meihua Dang, Linxin Song, Honghua Zhang, Jieyu Zhao +2 more

The paper proposes a novel probabilistic globally constrained decoding (P-GCD) method that efficiently constructs proposals for locally constrained decoding, significantly improving convergence speed…

View →
cs.CRcs.AIRecentApr 12, 2026

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

Xuwei Ding, Skylar Zhai, Linxin Song, Jiate Li +5 more

The paper introduces OS-BLIND, a benchmark demonstrating that current safety evaluations fail to detect critical vulnerabilities in computer-use agents when user instructions are benign, showing high…

View →