10 papers
Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
Yinlin Zhu, Di Wu, Yi Zhang +5
Multimodal-attributed graphs (MAGs), where nodes carry heterogeneous semantic content across multiple modalities while edges encode relational dependencies, have been widely adopte…
RHEA: Reliability-Harmonized Reconstruction and Assignment for Robust Multimodal-Attributed Graph Clustering
Yinlin Zhu, Di Wu, Ziyu Han +4
Multimodal-attributed graphs (MAGs), whose nodes carry heterogeneous attributes such as text and images over a relational structure, have become a fundamental substrate for label-f…
Both Topology and Text Matter: Revisiting LLM-guided Out-of-Distribution Detection on Text-attributed Graphs
Yinlin Zhu, Di Wu, Xu Wang +2
Text-attributed graphs (TAGs) associate nodes with textual attributes and graph structure, enabling GNNs to jointly model semantic and structural information. Although effective on…
GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
Yunqiang Wang, Hengyuan Na, Di Wu +2
Audio Large Language Models (ALLMs) enable spoken interaction but introduce new jailbreak vulnerabilities. Existing perturbation-based jailbreaks do not explicitly control which fr…
TMTE: Effective Multimodal Graph Learning with Task-aware Modality and Topology Co-evolution
Yinlin Zhu, Xunkai Li, Di Wu +3
Multimodal-attributed graphs (MAGs) are a fundamental data structure for multimodal graph learning (MGL), enabling both graph-centric and modality-centric tasks. However, our empir…
Adapter-Augmented Bandits for Online Multi-Constrained Multi-Modal Inference Scheduling
Xianzhi Zhang, Yue Xu, Yinlin Zhu +4
Multi-modal large language model (MLLM) inference scheduling enables strong response quality under practical and heterogeneous budgets, beyond what a homogeneous single-backend set…