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

Xi Xiao

4 indexed papers

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

Publications per year

4
26

Top categories

AI×4Crypto×2NLP×1ML×1

Frequent co-authors

Zhikai Pan2×
Chih-Ting Liao2×
Chunrui Liu2×
Yitong Qiao2×
Chunlei Meng2×
Zhangquan Chen2×

Research Timeline

2026
DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

DCVD proposes a dual-channel cross-modal fusion framework that jointly detects software vulnerabilities and precisely localizes the vulnerable lines, outperforming existing state-of-the-art methods.

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memory is the primary bottleneck.

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memory is the primary bottleneck.

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

The paper proposes Routing-based On-Policy Distillation (ROPD), a novel realignment framework for large language models that addresses the limitations of existing safety-realignment defenses.

Highlighted terms show continued research focus across papers

Papers

cs.AIcs.CLcs.CREmpiricalRecentJul 29, 2026

On-Policy Distillation for LLM Safety: A Routing Approach to Template-Robust Realignment

Yongjian Guo, Wanlun Ma, Lingyu Shen, Xi Xiao +1 more

The paper proposes Routing-based On-Policy Distillation (ROPD), a novel realignment framework for large language models that addresses the limitations of existing safety-realignment defenses.

View →
cs.AIRecent
May 27, 2026

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

Zhikai Pan, Chih-Ting Liao, Chunrui Liu, Xi Xiao +4 more

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

View →
cs.AIRecentMay 27, 2026

Do LLMs Build World Models From Text? A Multilingual Diagnostic of Spatial Reasoning

Zhikai Pan, Chih-Ting Liao, Chunrui Liu, Xi Xiao +4 more

The paper introduces a multilingual benchmark (MentalMap) to test if LLMs build internal spatial world models from text, finding a universal 'L3 reasoning cliff' suggesting that text-only working memo…

View →
cs.CRcs.AIMay 10, 2026

DCVD: Dual-Channel Cross-Modal Fusion for Joint Vulnerability Detection and Localization

Wenxin Tang, Wenbin Li, Junliang Liu, Jingyu Xiao +9 more

DCVD proposes a dual-channel cross-modal fusion framework that jointly detects software vulnerabilities and precisely localizes the vulnerable lines, outperforming existing state-of-the-art methods.

View →