Scholar
Xiangzheng Zhang
Google Scholar ID: da0Y7jUAAAAJ
360
AI safety
Large language models
Information Retrieval
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
136
H-index
5
i10-index
3
Publications
10
Co-authors
4
list available
Publications
46 items
From Latents to Wires: Surgical Post-Editing on Large Language Models
2026
Cited
0
ScienceArena: Benchmarking LLMs on Latest Scientific Olympiad Competitions
2026
Cited
0
ArborMem: Navigating Interaction States with Memory Forests
2026
Cited
0
When Do Prompt-Side Agent Playbooks Transfer? Accuracy, Cost, and Runtime Shift in Agent Deployment
2026
Cited
0
SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent Skills
2026
Cited
0
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
2026
Cited
0
Dynamic Defense Profiling Enables Cognitive Jailbreak of Text-to-Image Models
2026
Cited
0
ElephantAgent: Contextual State Continuity in Agentic Systems
2026
Cited
0
Load more
Co-authors
4 total
Haosheng Zou
Tsinghua University
Lin Sun
Qihoo 360
Guangxiang Zhao
Peking University
Shousheng Jia
360
