Lilan Peng
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
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.
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.
Papers
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.