Skip to content

Author

Ouxiang Li

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Oct 2026

HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse Evidence

Agent harnesses play a critical role in defenses by enforcing safety constraints to prevent unsafe actions. However, rapidly emerging attacks outpace manual harness adaptation, motivating automated harness evolution. Yet the signals available for harness evolution are often sparse, such as brief descriptions or a few a...

Xi-Qiao Xiong, Mo-Xin Li, Zhi-Xin Ma et al. · 0 citations
Preprint Aug 2026

PEAK: Precise and Persistent Concept Erasure via k-Sparse Autoencoders

Erasing concepts from large-scale text-to-image (T2I) diffusion models has become increasingly crucial due to the growing concerns over copyright infringement, privacy violations, and offensive content. Existing approaches struggle to achieve both precise and persistent concept erasure: inaccurate localization of conce...

Man Jiang, Ouxiang Li, Weibao Xue et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.