401 citations · 493 across the 12 of their papers we have counts for
13 papers
Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs
Chengyu Xie, Fei Shen, Shuyi Miao +5
The safety capabilities of large language models (LLMs) are highly uneven across different languages, often allowing cross-lingual attacks to bypass safety guardrails. Existing ali…
SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs
Jian Yu, Fei Shen, Cong Wang +5
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…
MGNet: Learning Correspondences via Multiple Graphs
Luanyuan Dai, Xiaoyu Du, Hanwang Zhang +1
Learning correspondences aims to find correct correspondences (inliers) from the initial correspondence set with an uneven correspondence distribution and a low inlier rate, which…
Triplet Contrastive Representation Learning for Unsupervised Vehicle Re-identification
Fei Shen, Xiaoyu Du, Liyan Zhang +2
Part feature learning is critical for fine-grained semantic understanding in vehicle re-identification. However, existing approaches directly model part features and global feature…
BiSTNet: Semantic Image Prior Guided Bidirectional Temporal Feature Fusion for Deep Exemplar-based Video Colorization
Yixin Yang, Zhongzheng Peng, Xiaoyu Du +3
How to effectively explore the colors of reference exemplars and propagate them to colorize each frame is vital for exemplar-based video colorization. In this paper, we present an…
Modeling Embedding Dimension Correlations via Convolutional Neural Collaborative Filtering
Xiaoyu Du, Xiangnan He, Fajie Yuan +3
As the core of recommender system, collaborative filtering (CF) models the affinity between a user and an item from historical user-item interactions, such as clicks, purchases, an…
Fast Matrix Factorization with Non-Uniform Weights on Missing Data
Xiangnan He, Jinhui Tang, Xiaoyu Du +3
Matrix factorization (MF) has been widely used to discover the low-rank structure and to predict the missing entries of data matrix. In many real-world learning systems, the data m…
Adversarial Training Towards Robust Multimedia Recommender System
Jinhui Tang, Xiaoyu Du, Xiangnan He +3
With the prevalence of multimedia content on the Web, developing recommender solutions that can effectively leverage the rich signal in multimedia data is in urgent need. Owing to…
Outer Product-based Neural Collaborative Filtering
Xiangnan He, Xiaoyu Du, Xiang Wang +3
In this work, we contribute a new multi-layer neural network architecture named ONCF to perform collaborative filtering. The idea is to use an outer product to explicitly model the…
Adversarial Personalized Ranking for Recommendation
Xiangnan He, Zhankui He, Xiaoyu Du +1
Item recommendation is a personalized ranking task. To this end, many recommender systems optimize models with pairwise ranking objectives, such as the Bayesian Personalized Rankin…