5 papers
Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs
Chengyu Xie, Fei Shen, Shuyi Miao +5
The safety capabilities of large language models (LLMs) are highly uneven across different languages, often allowing cross-lingual attacks to bypass safety guardrails. Existing ali…
ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs
Xianhui Zhang, Jian Yu, Chengyu Xie +6
Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jailbreak attacks in non-high-re…
IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection
Fei Shen, Chengyu Xie, Lihong Wang +5
Existing multi-turn image editing paradigms are often confined to isolated single-step execution. Due to a lack of context-awareness and closed-loop feedback mechanisms, they are p…
Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons
Xianhui Zhang, Chengyu Xie, Linxia Zhu +6
Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanis…
Jointly Conditioned Diffusion Model for Multi-View Pose-Guided Person Image Synthesis
Chengyu Xie, Zhi Gong, Junchi Ren +4
Pose-guided human image generation is limited by incomplete textures from single reference views and the absence of explicit cross-view interaction. We present jointly conditioned…