Tie, Guiyao

2 publications

NeurIPS 2025 BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization Xueyang Zhou, Guiyao Tie, Guowen Zhang, Hecheng Wang, Pan Zhou, Lichao Sun

NeurIPS 2025 Can LLMs Correct Themselves? a Benchmark of Self-Correction in LLMs Guiyao Tie, Zenghui Yuan, Zeli Zhao, Chaoran Hu, Tianhe Gu, Ruihang Zhang, Sizhe Zhang, Junran Wu, Xiaoyue Tu, Ming Jin, Qingsong Wen, Lixing Chen, Pan Zhou, Lichao Sun