Get started
Author

Zhihua Wei

Observed name: Wei, Zhihua
Institution: Tongji University
Observed institution: Tongji University
OpenAlex ID: A5124004045
VCN-Bench: A Video-Contextualized Navigation Benchmark for Spatial Reasoning over Prior Visual Experience
2026 · Zhang, Siqi, Wei, Meng, et al. · arXiv (Cornell University)
PDF
Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructions
2026 · Wang, Qingzhuo, Wang, CaiYi, et al. · arXiv (Cornell University)
PDF
AlphaDiverse: Post-Training Local Quantitative Research Agents for Diverse Exploration in Alpha Factor Mining
2026 · Wang, Qingzhuo, Wei, Zikun, et al. · arXiv (Cornell University)
PDF
Evaluating and Explaining Prompt Sensitivity of LLMs Using Interactions
2026 · Qin, Ruiyang, Wang, Qingzhuo, et al. · arXiv (Cornell University)
PDF
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
2026 · Association for Computational Linguistics 2026, Li, Qiang, et al. · Underline Science Inc.
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
2026 · Qin, Zhenxin, Li, Qiang, et al. · arXiv (Cornell University)
PDF
A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions
2026 · Wang, Qingzhuo, Qin, Ruiyang, et al. · arXiv (Cornell University)
PDF
Multilingual Safety Alignment via Self-Distillation
2026 · Qin, Ruiyang, Wang, Qingzhuo, et al. · arXiv (Cornell University)
PDF
TME-PSR: Time-aware, Multi-interest, and Explanation Personalization for Sequential Recommendation
2026 · Wang, Qingzhuo, Wen, Leilei, et al. · arXiv (Cornell University)
PDF
Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift
2026 · Wei, Zhihua, Li, Qiang, et al. · arXiv (Cornell University)
PDF
AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
2026 · Liu, Dongrui, Ren, Qihan, et al. · arXiv (Cornell University)
PDF
Mitigating Action-Relation Hallucinations in LVLMs via Relation-aware Visual Enhancement
2026 · Zhenxin Qin, Qiang Li, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Works count: 12
Citation count:
H-index:
I10-index:
Year
Topic
Type