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

Wanlong Fang

3 indexed papers

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

Publications per year

3
26

Top categories

AI×3Crypto×2Vision×2

Frequent co-authors

Xiang Fang2×
Tianle Zhang1×
Wen Tao1×
Alvin Chan1×

Research Timeline

2026
Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85% reduction in harmful outputs.

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85% reduction in harmful outputs.

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal language models, revealing distinct modality-use profiles for different task types.

Highlighted terms show continued research focus across papers

Papers

cs.AIRecentMay 31, 2026

Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition

Wanlong Fang, Tianle Zhang, Wen Tao, Alvin Chan

The paper introduces Partial Information Decomposition (PID) to quantitatively separate unique, redundant, and synergistic contributions of different modalities (e.g., vision, language) in multimodal…

View →
cs.CRcs.AIcs.CVRecentMay 27, 2026

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Xiang Fang, Wanlong Fang

The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85% reduction…

View →
cs.CRcs.AIcs.CVRecentMay 27, 2026

Disentangling Adversarial Prompts: A Semantic-Graph Defense for Robust LLM Security

Xiang Fang, Wanlong Fang

The paper proposes the Adversarial Prompt Disentanglement (APD) framework, a novel defense mechanism that proactively identifies and neutralizes malicious components in LLM prompts, achieving over 85%…

View →