3 papers
cs.CR2025
Ghost in the Transformer: Detecting Model Reuse with Invariant Spectral Signatures
Suqing Wang, Ziyang Ma, Li Xinyi +1
Large Language Models (LLMs) are widely adopted, but their high training cost leads many developers to fine-tune existing open-source models. While most adhere to open-source licen…
cs.CV2025
CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
Zicong Tang, Ziyang Ma, Suqing Wang +5
Large Vision-Language Models (LVLMs) process multimodal inputs consisting of text tokens and vision tokens extracted from images or videos. Due to the rich visual information, a si…
cs.CL2025
Model Hemorrhage and the Robustness Limits of Large Language Models
Ziyang Ma, Zuchao Li, Lefei Zhang +4
Large language models (LLMs) demonstrate strong performance across natural language processing tasks, yet undergo significant performance degradation when modified for deployment t…