16 papers
HiRoute: Hierarchical Routed Prompt Tuning for Safety Alignment of Large Language Models
Fangzhou Chen, Shiji Zhao, Mengyang Wang +4
Large language models (LLMs) remain vulnerable to harmful requests and jailbreak attacks. Parameter-efficient safety alignment methods based on prompt tuning typically rely on a si…
A Multimodal Automatic Redteaming Evaluation based on Atomic Jailbreak Strategy Decoupling and Combination
Shiji Zhao, Yuxuan Zhou, Chen Xiong +3
Multimodal Large Language Models (MLLMs) have achieved impressive progress in image-text comprehension and generation, yet they remain susceptible to jailbreak attacks that can tri…
VQ-Jarvis: Retrieval-Augmented Video Restoration Agent with Sharp Vision and Fast Thought
Xuanyu Zhang, Weiqi Li, Qunliang Xing +6
Video restoration in real-world scenarios is challenged by heterogeneous degradations, where static architectures and fixed inference pipelines often fail to generalize. Recent age…
Improving Safety Alignment via Balanced Direct Preference Optimization
Shiji Zhao, Mengyang Wang, Shukun Xiong +7
With the rapid development and widespread application of Large Language Models (LLMs), their potential safety risks have attracted widespread attention. Reinforcement Learning from…
Mind over Space: Can Multimodal Large Language Models Mentally Navigate?
Qihui Zhu, Shouwei Ruan, Xiao Yang +6
Despite the widespread adoption of MLLMs in embodied agents, their capabilities remain largely confined to reactive planning from immediate observations, consistently failing in sp…
Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective
Maoxun Yuan, Duanni Meng, Ziteng Xi +4
Infrared small target detection and segmentation (IRSTDS) is a critical yet challenging task in defense and civilian applications, owing to the dim, shapeless appearance of targets…