SOURCE-LINKED INTELLIGENCE

SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

Existing safety alignment methods for vision-language models usually modify the model behavior globally: once the safety parameters are trained or loaded, they participate in both unsafe and already-safe generations. This always-on intervention can unnecessarily perturb the model's original reasoning path and degrade general multimodal capabilities. We argue that safety alignment should be an on-demand intervention rather than a permanent modification to every decoding trajectory. To this end, we propose a streaming recognition and gated LoRA framework for intrinsic VLM safety. During autoregr

Read original source ↗ Open in workspace

recordType

paper

region

Global