Text adversarial attack methods are typically designed for static scenarios with fixed numbers of output labels and a predefined label space, relying on extensive querying of the victim model (query-based attacks) or the surrogate model (transfer-based attacks). However, real-world applications often involve non-static...
Wen-Qiang Wang, Si-Yuan Liang, Yangshijie Zhang et al.· IEEE Transactions on Informa...· 2 citations
A new multimodal ICL framework is proposed that combines contrastive demonstration modeling with the self-refinement capability of MLLMs and consistently improves MLLM performance, with particularly notable gains on visual question answering (VQA).
Ming-Bo Yang, Wen-Qiang Wang, Zhaolu Kang et al.· 1 citation
This work introduces a Variational Semantic Prompt Extractor (VSPE), which adaptively aggregates anomaly-relevant local semantics from dense patch tokens and regularizes them through a variational information bottleneck, thereby incorporating fine-grained visual cues and enabling more precise cross-modal alignment.
Peng Chen, Kai-Ge Li, Wei Wang et al.· arXiv.org· 0 citations
Performance-Driven Demonstration Selection (PDDS), which directly aligns demonstration selection with ICL performance, is proposed, which formulates selection as predicting the target LLM’s downstream task performance for a given query–in-context pair, replacing proxy heuristics with a performance-aware objec-tive.
Wen-Qiang Wang, Ming-Bo Yang, Ai-Ping Zhang et al.· Proceedings of the Thirty-Fi...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
