81 citations · 102 across the 7 of their papers we have counts for
8 papers
Paper Summary Attack: Jailbreaking LLMs through LLM Safety Papers
Liang Lin, Zhihao Xu, Xuehai Tang +5
The safety of large language models (LLMs) has garnered significant research attention. In this paper, we argue that previous empirical studies demonstrate LLMs exhibit a propensit…
Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target Tokens
Xikang Yang, Xuehai Tang, Fuqing Zhu +2
Vision-language models (VLMs) seamlessly integrate visual and textual data to perform tasks such as image classification, caption generation, and visual question answering. However…
Semantic-Enhanced Relational Metric Learning for Recommender Systems
Mingming Li, Fuqing Zhu, Feng Yuan +1
Recently, relational metric learning methods have been received great attention in recommendation community, which is inspired by the translation mechanism in knowledge graph. Diff…
Hateful Memes Detection via Complementary Visual and Linguistic Networks
Weibo Zhang, Guihua Liu, Zhuohua Li +1
Hateful memes are widespread in social media and convey negative information. The main challenge of hateful memes detection is that the expressive meaning can not be well recognize…
AutoSUM: Automating Feature Extraction and Multi-user Preference Simulation for Entity Summarization
Dongjun Wei, Yaxin Liu, Fuqing Zhu +4
Withthegrowthofknowledgegraphs, entity descriptions are becoming extremely lengthy. Entity summarization task, aiming to generate diverse, comprehensive, and representative summari…
Pre-training Text Representations as Meta Learning
Shangwen Lv, Yuechen Wang, Daya Guo +10
Pre-training text representations has recently been shown to significantly improve the state-of-the-art in many natural language processing tasks. The central goal of pre-training…
Pseudo-positive regularization for deep person re-identification
Fuqing Zhu, Xiangwei Kong, Haiyan Fu +1
An intrinsic challenge of person re-identification (re-ID) is the annotation difficulty. This typically means 1) few training samples per identity, and 2) thus the lack of diversit…
Part-based Deep Hashing for Large-scale Person Re-identification
Fuqing Zhu, Xiangwei Kong, Liang Zheng +2
Large-scale is a trend in person re-identification (re-id). It is important that real-time search be performed in a large gallery. While previous methods mostly focus on discrimina…