Get started
Author

Tianzhuo Yang

Observed name: Yang, Tianzhuo
Institution: Peking University
Observed institution: Peking University
OpenAlex ID: A5128222875
DANGERLENS: Probing Dangerous Representations Hidden by Safety Alignment
2026 · Yang, Tianzhuo, Yan, Shaoheng, et al. · arXiv (Cornell University)
PDF
AgentBoundary: Counterfactual Evaluation of Safety in Tool-Using LLM Agents
2026 · Yang, Tianzhuo, Mi, Zirui, et al. · arXiv (Cornell University)
PDF
A novel strategy for achieving a low-field lightweight permanent MRI magnet system with good magnetic field homogeneity and low eddy current
2026 · Jingzhi Han, Jiangqian Guo, et al. · Chinese Physics B
PDF
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
2026 · Wang, Lichao, Ren, Zhaoxing, et al. · arXiv (Cornell University)
PDF
MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models
2026 · Yang, Tianzhuo, Shen, Zihan, et al. · arXiv (Cornell University)
PDF
VISA: Value Injection via Shielded Adaptation for Personalized LLM Alignment
2026 · Jiawei Chen, Tianzhuo Yang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
Stable Reasoning, Unstable Responses: Mitigating LLM Deception via Stability Asymmetry
2026 · Guoxi Zhang, Jiawei Chen, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
2026 · Lichao Wang, ZhaoXing Ren, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 8
Citation count:
H-index:
I10-index:
Year
Topic
Type