2 papers
cs.AI2026
Safety Geometry Collapse in Multimodal LLMs and Adaptive Drift Correction
Jiahe Guo, Xiangran Guo, Jiaxuan Chen +6
Multimodal large language models (MLLMs) often fail to transfer safety capabilities learned in the text modality to semantically equivalent non-text inputs, revealing a persistent…
cs.AI2026
When Personalization Legitimizes Risks: Uncovering Safety Vulnerabilities in Personalized Dialogue Agents
Jiahe Guo, Xiangran Guo, Yulin Hu +8
Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized agents prioritizes utility and use…