5 papers · 1 filter
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs
Jian Yu, Fei Shen, Cong Wang +5
Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes a significant gap between e…
OPD-V: Visual On-Policy Self-Distillation with Modality Balance
Aniri, Jinhe Bi, Peng Liao +5
On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (MLLMs). Existing methods draw pr…
Suppressing Forgery-Specific Shortcuts for Generalizable Deepfake Detection
Yihui Wang, Yonghui Yang, Jilong Liu +3
Deepfake detection suffers from poor generalization across forgery methods, as existing models tend to rely on spurious method-specific shortcuts that fail to transfer to unseen ma…
Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models
Enyi Shi, Fei Shen, Chuancheng Shi +5
With the widespread deployment of vision-language large models (VLLMs), their safety alignment faces dual challenges across languages and modalities. Existing methods model multili…
Active Zero: Self-Evolving Vision-Language Models through Active Environment Exploration
Jinghan He, Junfeng Fang, Feng Xiong +5
Self-play has enabled large language models to autonomously improve through self-generated challenges. However, existing self-play methods for vision-language models rely on passiv…