PixelBytes: Catching Unified Embedding for Multimodal Generation - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2024

PixelBytes: Catching Unified Embedding for Multimodal Generation

Fabien Furfaro
  • Fonction : Auteur

Résumé

This report introduces PixelBytes Embedding, a novel approach for unified multimodal representation learning. Our method captures diverse inputs in a single, cohesive representation, enabling emergent properties for multimodal sequence generation, particularly for text and pixelated images. Inspired by state-of-the-art sequence models such as Image Transformers, PixelCNN, and Mamba-Bytes, PixelBytes aims to address the challenges of integrating different data types. We explore various model architectures, including Recurrent Neural Networks (RNNs), State Space Models (SSMs), and Attention-based models, focusing on bidirectional processing and our innovative PxBy embedding technique. Our experiments, conducted on a specialized PixelBytes Pokémon dataset, demonstrate that bidirectional sequence models with PxBy embedding and convolutional layers can generate coherent multimodal sequences. This work contributes to the advancement of integrated AI models capable of understanding and generating multimodal data in a unified manner.
Fichier principal
Vignette du fichier
preprint.pdf (1.97 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04683349 , version 1 (02-09-2024)
hal-04683349 , version 2 (14-09-2024)

Licence

Identifiants

Citer

Fabien Furfaro. PixelBytes: Catching Unified Embedding for Multimodal Generation. 2024. ⟨hal-04683349v1⟩
162 Consultations
31 Téléchargements

Altmetric

Partager

More