activity
20242026
collaborators

11 papers

cs.LG2026

Gated Graph Attention Networks with Learnable Temperature

Zhongtian Ma, Hao Wu, Yexin Zhang +2

Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed s…

cs.AI2026

AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security

Dongrui Liu, Yu Li, Zhonghao Yang +47

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mod…

cs.LG2026

Matrix Completion with Hypergraphs:Sharp Thresholds and Efficient Algorithms

Zhongtian Ma, Qiaosheng Zhang, Zhen Wang

This paper considers the problem of completing a rating matrix based on sub-sampled matrix entries as well as observed social graphs and hypergraphs. We show that there exists a \e…

cs.LG2026

Misclassification Rate and Privacy-Utility Trade-offs in Graph Convolutional Networks via Subsampling Stability

Yexin Zhang, Zhongtian Ma, Qiaosheng Zhang +1

We study differential privacy (DP) in Graph Convolutional Networks (GCNs) through the framework of \textit{subsampling stability}. We derive upper bounds on the misclassification r…

cs.LG2025

Graph Feedback Bandits on Similar Arms: With and Without Graph Structures

Han Qi, Fei Guo, Li Zhu +1

In this paper, we study the stochastic multi-armed bandit problem with graph feedback. Motivated by applications in clinical trials and recommendation systems, we assume that two a…

cs.AI2025

PerPilot: Personalizing VLM-based Mobile Agents via Memory and Exploration

Xin Wang, Zhiyao Cui, Hao Li +10

Vision language model (VLM)-based mobile agents show great potential for assisting users in performing instruction-driven tasks. However, these agents typically struggle with perso…