Get started
Author

Jing Shao

Frequency-Domain Regularized Adversarial Alignment for Transferable Attacks against Closed-Source MLLMs
2026 · Yuan, Leitao, Mao, Qinghua, et al. · arXiv (Cornell University) · 1
PDF
ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis
2026 · Li, Yu, Luo, Haoyu, et al. · arXiv (Cornell University) · 1
PDF
OwlSight: A Panoramic Monitor for Chain-of-Thought Reasoning
2026 · Yan, Lewen, Zhu, Yanxu, et al. · arXiv (Cornell University)
PDF
TRAP: Tool-result Replay Attack for Probing Misbinding in LLM Agents
2026 · Zhi, Yutong, Zhang, Jie, et al. · arXiv (Cornell University)
PDF
Who Judges the Judges? A Chinese Safety QA Benchmark for Evaluating LLM Responses and Safety Judges
2026 · Yang, Rui, Huang, Shuang, et al. · arXiv (Cornell University)
PDF
MobileWorldSafety: Benchmarking GUI Agent Safety Against Environmental Injection Attacks in Android Apps
2026 · Chen, Sujin, Li, Lijun, et al. · arXiv (Cornell University)
PDF
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
2026 · Qu, Wanying, Mao, Qinghua, et al. · arXiv (Cornell University)
PDF
Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations
2026 · Feng, Xinshun, Miao, Ziqi, 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
Mitigating Scaffolding Collapse in Socratic Tutors via Representation Alignment
2026 · Shao, Jing, Wu, Qifeng, et al. · arXiv (Cornell University)
PDF
READER: Dynamic LLM Provenance from Query-Varying Interactions
2026 · Liu, Jiaxu, Mu, Sunnan, et al. · arXiv (Cornell University)
PDF
ReasonAny: Incorporating Reasoning Capability to Any Model via Simple and Effective Model Merging
2026 · Association for Computational Linguistics 2026, Liu, Yong, et al. · Underline Science Inc.
COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation
2026 · Zhou, Tianyi, Liu, Dongrui, et al. · arXiv (Cornell University)
PDF
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
2026 · Liu, Dongrui, Li, Yu, et al. · arXiv (Cornell University)
PDF
AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
2026 · Ye, Yulei, Li, Wenhao, et al. · arXiv (Cornell University)
PDF
UniACE: A Unified Framework for Evaluating LLM Agentic Capabilities
2026 · Zhu, Pengyu, Li, Lijun, et al. · arXiv (Cornell University)
PDF
What Do EEG Foundation Models Capture from Human Brain Signals?
2026 · Tang, Ling, Chen, Qian, et al. · arXiv (Cornell University)
PDF
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
2026 · Hu, Xuhao, Zhang, Xi, et al. · arXiv (Cornell University)
PDF
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
2026 · Ding, Shuangrui, Dai, Xuanlang, et al. · arXiv (Cornell University)
PDF
Safactory: A Scalable Agentic Infrastructure for Training Trustworthy Autonomous Intelligence
2026 · Chen, Xinquan, Yin, Zhenyun, et al. · arXiv (Cornell University)
PDF
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
2026 · Feng, Xinshun, Song, Xinhao, et al. · arXiv (Cornell University)
PDF
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
2026 · Ren, Qihan, Wang, Peng, et al. · arXiv (Cornell University)
PDF
DARE: Diffusion Large Language Models Alignment and Reinforcement Executor
2026 · Yang, Jingyi, Jiang, Yuxian, et al. · arXiv (Cornell University)
PDF
SafeSci: Safety Evaluation of Large Language Models in Science Domains and Beyond
2026 · Zhu, Xiangyang, Tian, Yuan, et al. · arXiv (Cornell University)
PDF
Frontier AI Risk Management Framework in Practice: A Risk Analysis Technical Report v1.5
2026 · Liu, Dongrui, Yu, Yi, et al. · arXiv (Cornell University)
PDF
Works count: 39
Citation count: 2
H-index: 1
I10-index:
Year
Topic
Type