4 papers
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs
Jian Yu, Fei Shen, Cong Wang +6
Although Large Language Models (LLMs) have demonstrated promising safety performance, extending them to Multimodal Large Language Models (MLLMs) exposes a significant gap between e…
LeCoT: revisiting network architecture for two-view correspondence pruning
Luanyuan Dai, Xiaoyu Du, Jinhui Tang
Two-view correspondence pruning aims to accurately remove incorrect correspondences (outliers) from initial ones and is widely applied to various computer vision tasks. Current pop…
TEST-V: TEst-time Support-set Tuning for Zero-shot Video Classification
Rui Yan, Jin Wang, Hongyu Qu +4
Recently, adapting Vision Language Models (VLMs) to zero-shot visual classification by tuning class embedding with a few prompts (Test-time Prompt Tuning, TPT) or replacing class n…
Precision Profile Pollution Attack on Sequential Recommenders via Influence Function
Xiaoyu Du, Yingying Chen, Yang Zhang +1
Sequential recommendation approaches have demonstrated remarkable proficiency in modeling user preferences. Nevertheless, they are susceptible to profile pollution attacks (PPA), w…