Publications

2026

1. arXiv

   Efficient LLM Adversarial Training via Low-Rank Defense and Circuit-Guided Surrogates

   Weiyi He*, Yuping Lin, Jiliang Tang, Yue Xing

   arXiv preprint arXiv:2607.28959, 2026

   Paper
2. arXiv

   AURA: Adaptive Uncertainty-aware Refinement for LLM-as-a-Judge Auditing

   Zilong Zhang, Yi-Ting Hung, Weiyi He, Junxi Zhang, Lei Ding, Chi-Kuang Yeh

   arXiv preprint arXiv:2606.19714, 2026

   Paper
3. AISTATS 2026

   Impact of Positional Encoding: Clean and Adversarial Rademacher Complexity for Transformers under In-Context Regression

   Weiyi He*, Yue Xing

   International Conference on Artificial Intelligence and Statistics (AISTATS), 2026

   Paper Poster Slides

2025

1. ACL 2025

   Unveiling privacy risks in llm agent memory

   Bo Wang, Weiyi He, Shenglai Zeng, Zhen Xiang, Yue Xing, Jiliang Tang, Pengfei He

   Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025

   Paper Code