Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Qi Cao

Qi Cao

4 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

Crypto×2AI×2Networking×1ML×1

Frequent co-authors

Ruiyi Zhang2×
Pengtao Xie2×
Zongyao Huang1×
Fan Yang1×
Yulin Shao1×
Shuhao Zhang1×

Research Timeline

2026
Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off

The paper theorizes that aligned LLMs remain jailbreakable due to 'Refusal-Escape Directions' (RED), which are continuous perturbation paths that shift model behavior from refusal to answering, and shows this vulnerability is linked to specific operator-level sources within the model architecture.

AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-the-art performance on benchmark tasks.

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

The paper introduces SCOUT, a dynamic detector allocation framework that improves prompt-injection defense by predicting detector reliability and latency to optimize the trade-off between safety and operational utility.

From Partitioning to Provisioning: Co-Designing DNN Deployment and Infrastructure Capacity

One clear sentence describing what this paper does

Highlighted terms show continued research focus across papers

Papers

cs.NIEmpiricalRecentOct 20, 2026

From Partitioning to Provisioning: Co-Designing DNN Deployment and Infrastructure Capacity

Zongyao Huang, Fan Yang, Qi Cao, Yulin Shao

One clear sentence describing what this paper does

View →
cs.CRcs.LGRecentMay 29, 2026

Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection Defense

Shuhao Zhang, Jiarui Li, Qi Cao, Ruiyi Zhang +1 more

The paper introduces SCOUT, a dynamic detector allocation framework that improves prompt-injection defense by predicting detector reliability and latency to optimize the trade-off between safety and o…

View →
cs.AIRecentMay 27, 2026

AIBuildAI-2: A Knowledge-Enhanced Agent for Automatically Building AI Models

Ruiyi Zhang, Peijia Qin, Qi Cao, Li Zhang +1 more

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-t…

View →
cs.CRcs.AIMay 9, 2026

Why Do Aligned LLMs Remain Jailbreakable: Refusal-Escape Directions, Operator-Level Sources, and Safety-Utility Trade-off

Yu Chen, Yuanhao Liu, Qi Cao

The paper theorizes that aligned LLMs remain jailbreakable due to 'Refusal-Escape Directions' (RED), which are continuous perturbation paths that shift model behavior from refusal to answering, and sh…

View →