8 papers
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…
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…
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…
Disentangling Intent from Role: Adversarial Self-Play for Persona-Invariant Safety Alignment
Jiajia Li, Xiaoyu Wen, Zhongtian Ma +3
The growing capabilities of large language models (LLMs) have driven their widespread deployment across diverse domains, even in potentially high-risk scenarios. Despite advances i…
CiQi-Agent: Aligning Vision, Tools and Aesthetics in Multimodal Agent for Cultural Reasoning on Chinese Porcelains
Wenhan Wang, Zhixiang Zhou, Zhongtian Ma +8
The connoisseurship of antique Chinese porcelain demands extensive historical expertise, material understanding, and aesthetic sensitivity, making it difficult for non-specialists…
MAGIC: A Co-Evolving Attacker-Defender Adversarial Game for Robust LLM Safety
Xiaoyu Wen, Zhida He, Han Qi +7
Ensuring robust safety alignment is crucial for Large Language Models (LLMs), yet existing defenses often lag behind evolving adversarial attacks due to their \textbf{reliance on s…