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

Lilan Peng

2 indexed papers

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2ML×1Neural Computing×1Crypto×1

Frequent co-authors

Yandi Liu1×
Qingren Yao1×
Chongshou Li1×
Tianrui Li1×
Kun Wang1×
Cheng Qian1×

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.

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting

This paper proposes a novel pre-training plugin called MP3 to improve spatio-temporal forecasting performance by addressing the issue of temporal mirages in urban data.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.NEEmpiricalRecentJun 11, 2026

MP3: Multi-Period Pattern Pre-training forSpatio-Temporal Forecasting

Lilan Peng, Yandi Liu, Qingren Yao, Chongshou Li +1 more

This paper proposes a novel pre-training plugin called MP3 to improve spatio-temporal forecasting performance by addressing the issue of temporal mirages in urban data.

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 →