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

Cheng Yang

5 indexed papers

Recent (6 mo)
4
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

AI×3NLP×2Vision×2Software Eng.×2Crypto×1

Frequent co-authors

Xin Gao2×
Chufan Shi2×
Taylor Berg-Kirkpatrick2×
Zekai Yu2×
Qi Meng2×
Qizhi Chu2×

Research Timeline

2026
ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projector, causing a measurable semantic shift in poisoned inputs.

ParaTool: Shifting Tool Representations from Context to Parameters

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

ParaTool: Shifting Tool Representations from Context to Parameters

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.CVRecentMay 30, 2026

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

Xin Gao, Cheng Yang, Chufan Shi, Taylor Berg-Kirkpatrick

The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.

View →
cs.CLcs.CVRecentMay 30, 2026

Do Text Edits Generalize to Visual Generation? Benchmarking Cross-Modal Knowledge Editing in UMMs

Xin Gao, Cheng Yang, Chufan Shi, Taylor Berg-Kirkpatrick

The paper introduces UniKE, a benchmark showing that successful knowledge edits in text-only multimodal models do not reliably transfer to image generation, revealing a significant modality gap.

View →
cs.AIcs.SERecentMay 28, 2026

ParaTool: Shifting Tool Representations from Context to Parameters

Zekai Yu, Qi Meng, Qizhi Chu, Yu Hao +2 more

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

View →
cs.AIcs.SERecentMay 28, 2026

ParaTool: Shifting Tool Representations from Context to Parameters

Zekai Yu, Qi Meng, Qizhi Chu, Yu Hao +2 more

ParaTool introduces a novel framework that shifts tool representations from bulky context documentation to dedicated, loadable parameters, enabling efficient and robust tool calling in LLMs.

View →
cs.CRcs.AIApr 21, 2026

ProjLens: Unveiling the Role of Projectors in Multimodal Model Safety

Kun Wang, Cheng Qian, Miao Yu, Lilan Peng +5 more

The paper introduces ProjLens, an interpretability framework that reveals that backdoor vulnerabilities in Multimodal Large Language Models (MLLMs) are encoded within a low-rank subspace of the projec…

View →