Multimodal representation learning seeks shared representations for cross-modal retrieval and knowledge transfer. Hub-based binding reduces pairwise supervision costs, but separate hub connections cannot guarantee reliable alignment between modalities without direct joint training. We introduce Hub-Spectral Activation...
Yingying Guo, Hai-Dong Chen, Lin-Rui Xu et al.· 0 citations
With the rapid release of open-weight large foundation models, safety threats are shifting from black-box jailbreaks to neuron-level white-box attacks that directly identify and manipulate safety-related neurons. Existing alignment methods often investigate the safety behavior on a small number of neurons, creating fra...
Simiao Xie, Chuan-Cheng Shi, Shang-Ze Li et al.· 0 citations
As generated videos become increasingly realistic, reliable video forgery detection is increasingly important. Existing studies typically optimize and use video forgery detectors as black boxes, while the latent forgery-discriminative knowledge inside them remains largely unexplored. Instead of continuing to rely on re...
Shi-Chao Kan, Chengpeng Hong, Jingtong Dou et al.· 0 citations
HEIMAT, a HEurIstic-style autoMATic debiasing framework for LMs, effectively mitigates bias in different cultures while maintaining the model's natural language understanding (NLU) performance.
Tian Lan, Yemin Wang, Chuan-Cheng Shi et al.· 0 citations
A neuron-level cross-dimensional safety alignment framework driven by modality- and language-shared safety neurons (MLS-Neurons) that significantly outperforms state-of-the-art approaches across diverse multilingual and multimodal safety benchmarks while preserving general utility.
Enyi Shi, Fei Shen, Chuancheng Shi et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
