This paper presents OmniVL, a new foundation model to support both imagelanguage and video-language tasks using one universal architecture.

To be concrete, we firstly take the full self-attention and LayerNorm into consideration and derive a strict condition for eliminating the interference through a comprehensive analysis of the forward propagation of the ViT layer. Then we further propose to convert the condition of self-attention into its two sufficient conditions, which enables us to address the challenge of high order and nonlinearity.

Secure multi-party computation (MPC) allows parties to perform computations on data while keeping that data private. This capability has great potential for machine-learning applications: itfacilitates training ofmachine-learning models on private data sets owned by different parties, evaluation of one party's private model using another party'sprivatedata,etc. Although arange ofstudies implement machine-learning models via secure MPC, such implementations are not yetmainstream.