Realizing this vision is challenging due to two key reasons: 1) Expensive Storage.

Foundation models have emerged as powerful tools across various domains including language, vision, and multimodal tasks.

Despite their merits, a comprehensive comparison and synergistic application of them to a diverse model zoo is yet to be adequately addressed.

Harmful memes have proliferated on the Chinese Internet, while research on detecting Chinese harmful memes significantly lags behind due to the absence of reliable datasets and effective detectors. To this end, we focus on the comprehensive detection of Chinese harmful memes.

Releasing open-source large language models (LLMs) presents a dual-use risk since bad actors can easily fine-tune these models for harmful purposes. Even without the open release of weights, weight stealing and fine-tuning APIs make closed models vulnerable to harmful fine-tuning attacks (HFAs).