Get started
Author

Xiangzheng Zhang

Observed name: Zhang, Xiangzheng
OpenAlex ID: A5140985108
Harness-Bench: Evaluating Agent Harnesses across Models and Realistic Workflows
2026 · Yao, Yilun, Tan, Xinyu, et al. · arXiv (Cornell University) · 80
PDF
MemAudit: Post-hoc Auditing of Poisoned Agent Memory via Causal Attribution and Structural Anomaly Detection
2026 · Tan, Zhewen, Yao, Yilun, et al. · arXiv (Cornell University) · 10
PDF
RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions
2026 · Zongwei Lv, Yaoming Li, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 3
PDF
A Primer in Post-Training Reasoning Data: What We Know About How It Works
2026 · Li, Yaoming, Zhao, Guangxiang, et al. · arXiv (Cornell University) · 1
PDF
TrajShield: Trajectory-Level Safety Mediation for Defending Text-to-Video Models Against Jailbreak Attacks
2026 · Zou, Quanchen, Li, Nizhang, et al. · arXiv (Cornell University) · 1
PDF
BEAR: Budgeted Evidence Allocation for Multi-Document Reasoning
2026 · Lin Sun, Linglin Zhang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 1
PDF
ArborMem: Navigating Interaction States with Memory Forests
2026 · Lv, Zongwei, Xu, Yuemeng, et al. · arXiv (Cornell University)
PDF
TriPlay-RL: Tri-Role Self-Play Reinforcement Learning for LLM Safety Alignment
2026 · Association for Computational Linguistics 2026, Guan, Kaiqi, et al. · Underline Science Inc.
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
2026 · Association for Computational Linguistics 2026, ., Wangdexian, et al. · Underline Science Inc.
Thinking with Reasoning Skills: Fewer Tokens, More Accuracy
2026 · Association for Computational Linguistics 2026, Shi, Qilong, et al. · Underline Science Inc.
Reasoning-Oriented Programming: Chaining Semantic Gadgets to Jailbreak Large Vision Language Models
2026 · Zou, Quanchen, Chen, Moyang, et al. · arXiv (Cornell University)
PDF
Beyond Parameter Arithmetic: Sparse Complementary Fusion for Distribution-Aware Model Merging
2026 · Lin, Weihong, Sun, Lin, et al. · arXiv (Cornell University)
PDF
Beyond Static Alignment: Hierarchical Policy Control for LLM Safety via Risk-Aware Chain-of-Thought
2026 · Si, Jianfeng, Sun, Lin, et al. · arXiv (Cornell University)
PDF
Robust Privacy: Inference-Stage Privacy through Certified Robustness
2026 · Jin, Jiankai, Zhang, Xiangzheng, et al. · arXiv (Cornell University)
PDF
Works count: 14
Citation count: 96
H-index: 3
I10-index: 2
Year
Topic
Type