Can I read Scaling Law Hypothesis for Multimodal Model on EtoBox?

Scaling Law Hypothesis for Multimodal Model by Sun, Qingyun; Guo, Zhen; Team, PIN AI is a scholarly article available to read on EtoBox.

What is Scaling Law Hypothesis for Multimodal Model about?

We propose a scaling law hypothesis for multimodal models processing text, audio, images, and video within a shared token and embedding space. Our framework predicts model performance based on modality-specific compression and tokenization efficiency, extending established scaling laws from text-based decoder models to mixed-modality systems. We explore whether leveraging more training data in multiple modalities can reduce the size of the multimodal model, enabling efficient deployment on resource-constrained devices.

Author

Sun, Qingyun; Guo, Zhen; Team, PIN AI

Published

2024

Language

EN