Skip to content

Author

Kai Shu

We have 2 of 20 papers

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 Nov 2026

Compositional Unalignment: Auditing Safety in Large Vision-Language Models

CMaG is proposed, a training-free un-alignment method for compositional safety that measures refusal intention with a refusal-versus-compliance log-probability margin, takes its gradient with respect to mid-layer activations, and contrasts it against partially benign pairs to isolate the cross-modal interaction term.

H. Lee, Kai Shu, Li Xiong · 0 citations
Jul 2026

Dependency-Guided Code Generation: Structured Matrix Decomposition and Consistency-Guided Refinement

This work proposes a dependency-aware code generation framework that explicitly models interactions among code entities through a graph-based representation, and introduces a sparse triplet representation for strong dependencies, significantly improving storage efficiency and computational scalability.

Ming-Qiao Mo, Yangcheng Zeng, Zikai Xiao 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.