Guardado en:
Detalles Bibliográficos
Autores principales: Sun, Qingyun, Guo, Zhen, Team, PIN AI
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2409.06754
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915013842698240
author Sun, Qingyun
Guo, Zhen
Team, PIN AI
author_facet Sun, Qingyun
Guo, Zhen
Team, PIN AI
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_06754
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scaling Law Hypothesis for Multimodal Model
Sun, Qingyun
Guo, Zhen
Team, PIN AI
Machine Learning
Artificial Intelligence
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.
title Scaling Law Hypothesis for Multimodal Model
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2409.06754