Get started
Author

Peizhi Niu

Observed name: Niu, Peizhi
ORCID: 0009-0005-2157-2045
Observed ORCID: 0009-0005-2157-2045
OpenAlex ID: A5102687891
3DGS-IEval-15K: A Large-scale Image Quality Evaluation Database for 3D Gaussian-Splatting
2025 · Yuke Xing, Jiarui Wang, et al. · ACM International Conference on Multimedia (ACM MM) · 5
PDF
ModelVerification.jl: A Comprehensive Toolbox for Formally Verifying Deep Neural Networks
2025 · Tianhao Wei, Hanjiang Hu, et al. · Lecture notes in computer science · 5
PDF
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
2026 · WenHao Wang, Peizhi Niu, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting · 1
PDF
Making LLMs Truly Forget: Deep Unlearning by Searching, Selecting, and Severing Knowledge Paths
2026 · Wang, Jialu, Niu, Peizhi, et al. · arXiv (Cornell University)
PDF
What Must a World Model Distinguish for Planning?
2026 · Wei, Rongzhe, Hsu, Hans Hao-Hsun, et al. · arXiv (Cornell University)
PDF
Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens
2026 · Niu, Peizhi, Qu, Wenjie, et al. · arXiv (Cornell University)
PDF
MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools
2026 · Association for Computational Linguistics 2026, Chen, Zhaoyu, et al. · Underline Science Inc.
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
2026 · Wang, Wenhao, Niu, Peizhi, et al. · arXiv (Cornell University)
PDF
Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents
2026 · Al-Tawaha, Ahmad, Gu, Shangding, et al. · arXiv (Cornell University)
PDF
One Turn Too Late: Learning When to Intervene Against Multi-Turn Malicious Intent
2026 · Shen, Xinjie, Wei, Rongzhe, et al. · arXiv (Cornell University)
PDF
AgentSPEX: An Agent SPecification and EXecution Language
2026 · Wang, Pengcheng, Huang, Jerry, et al. · arXiv (Cornell University)
PDF
The Trojan Knowledge: Bypassing Commercial LLM Guardrails via Harmless Prompt Weaving and Adaptive Tree Search
2025 · Wei, Rongzhe, Niu, Peizhi, et al. · arXiv (Cornell University)
PDF
GUARD: Guided Unlearning and Retention via Data Attribution for Large Language Models
2025 · Niu, Peizhi, Ma, Evelyn, et al. · arXiv (Cornell University)
PDF
Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
2025 · Rongzhe Wei, Peizhi Niu, et al. · neural information processing systems
PDF
Graph Transductive Defense: a Two-Stage Defense for Graph Membership Inference Attacks
2024 · Niu, Peizhi, Pan, Chao, et al. · arXiv (Cornell University)
PDF
Works count: 16
Citation count: 11
H-index: 2
I10-index:
Year
Topic
Type