7 accepted papers
Small language models (SLMs) are increasingly deployed on edge devices, making their safety alignment crucial yet challenging. Current shallow alignment methods that rely on direct refusal of malicious queries fail to provide robust protection, particularly against adversarial jailbreaks. While deli
Brain-machine interfaces (BMIs) can enable humans to bypass the peripheral nervous system and directly control devices through the central nervous system. In this way, operators' hands are freed up, allowing them to interact with other devices, thus enabling multitasking operations. In this letter,
Automatic inspection of X-ray scans is a critical component of modern safety protocols. It plays an indispensable role in detecting concealed weapons, explosives, and other prohibited items that could pose a threat to public safety. Current surveillance systems perform poorly without human intervent…
We introduce LLaVA-MoD, a novel framework designed to enable the efficient training of small-scale Multimodal Language Models ($s$-MLLM) distilling knowledge from large-scale MLLM ($l$-MLLM). Our approach tackles two fundamental challenges in MLLM distillation. First, we optimize the network structu…
Reinforcement Learning from Human Feedback (RLHF) has become an essential technique for enhancing pre-trained large language models (LLMs) to generate responses that align with human preferences and societal values. Although RLHF has shown promise, the training of reward models (RMs) still faces the…
With the rapid development of various satellite sensor techniques, remote sensing imagery has been an important source of data in change detection applications. This paper aims to propose an unsupervised change detection method based on Object-based Markov Random Filed (OMRF) and Inception UNet (IUN…
Audio-Guided video semantic segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from background in a video sequence according to the referring audio expressions. However, the existing referring video semantic segmentation works mainl…