Product
Help
Pricing
About
Jobs
Log in
Get started
Author
Add to collection
Pengyu Zhu
Observed names:
Zhu, Pengyu,
Zhu, Pengyun
Institutions:
Beijing University of Posts and Telecommunications,
Tianjin University,
Shanghai Artificial Intelligence Laboratory
Observed institutions:
Beijing University of Posts and Telecommunications,
Tianjin University,
State Grid Corporation of China (China),
Shanghai Artificial Intelligence Laboratory
OpenAlex ID:
A5125020914
KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
2026
·
Lyu, Yaxing
, Zhou, Shengjie
, et al.
·
arXiv (Cornell University)
PDF
Is Deep Research Reliable? Misleading Knowledge Induces False Conclusions
2026
·
Zhu, Pengyu
, Li, Lijun
, et al.
·
arXiv (Cornell University)
PDF
DecIF: Improving Instruction-Following through Decomposition
2026
·
Association for Computational Linguistics 2026
, Dong, Guanting
, et al.
·
Underline Science Inc.
From Curated Data to Scalable Models: Continual Pre-training of Dense and MoE Large Language Models for Tibetan
2026
·
Association for Computational Linguistics 2026
, Chen, Yue
, et al.
·
Underline Science Inc.
UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities
2026
·
Zhu, Pengyu
, Li, Lijun
, et al.
·
arXiv (Cornell University)
PDF
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
2026
·
Hui, Tingfeng
, Xu, Hao
, et al.
·
arXiv (Cornell University)
PDF
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
2026
·
Miao Ziqi
, Lijun Li
, et al.
·
Proceedings of the AAAI Conference on Artificial Intelligence
PDF
"LLM Agent Performance" Is Not a Single Evaluation Target
2026
·
Zhu, Pengyu
, Sun, Li
, et al.
·
arXiv (Cornell University)
PDF
Response Attack: Exploiting Contextual Priming to Jailbreak Large Language Models
2026
·
Association for Artificial Intelligence 2026
, Li, Lijun
, et al.
·
Underline Science Inc.
SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
2026
·
Hao Li
, Jingkun An
, et al.
·
Conference on Empirical Methods in Natural Language Processing (EMNLP)
PDF
DecIF: Improving Instruction-Following through Decomposition
2026
·
Tingfeng Hui
, Pengyu Zhu
, et al.
·
Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
A Multi-Scale Graph Learning Method for Fault Diagnosis in Power Communication Networks
2025
·
Ning Li
, Pengyu Zhu
, et al.
·
International Conference on Advanced Cloud and Big Data
Show more works
View as search
Works count:
12
Citation count:
H-index:
I10-index:
Year
Topic
Type
