Guardado en:
Detalles Bibliográficos
Autor principal: Cesista, Franz Louis
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.11403
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910814459396096
author Cesista, Franz Louis
author_facet Cesista, Franz Louis
contents Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these modalities, such as document understanding. Moreover, finetuning these models and deploying them requires significantly more compute and more engineering effort than unimodal models. In this work, we present Multimodal Structured Generation, a framework that forces (frozen) MMFMs to produce outputs in a strictly structured format by applying hard constraints directly to the output logits. This approach not only ensures that the model generates parseable outputs that downstream APIs can easily ingest but also allows us to force the model to reason before answering, which significantly boosts performance without the need for expensive fine-tuning. We demonstrate the effectiveness of our method through competitive results in the CVPR 2nd MMFM Challenge, highlighting that carefully designed lightweight engineering can outperform expensive and complicated modeling approaches. All of our scripts, deployment steps, and evaluation results can be accessed in https://github.com/leloykun/MMFM-Challenge
format Preprint
id arxiv_https___arxiv_org_abs_2406_11403
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report
Cesista, Franz Louis
Computer Vision and Pattern Recognition
Computation and Language
Multimodal Foundation Models (MMFMs) have demonstrated strong performance in both computer vision and natural language processing tasks. However, their performance diminishes in tasks that require a high degree of integration between these modalities, such as document understanding. Moreover, finetuning these models and deploying them requires significantly more compute and more engineering effort than unimodal models. In this work, we present Multimodal Structured Generation, a framework that forces (frozen) MMFMs to produce outputs in a strictly structured format by applying hard constraints directly to the output logits. This approach not only ensures that the model generates parseable outputs that downstream APIs can easily ingest but also allows us to force the model to reason before answering, which significantly boosts performance without the need for expensive fine-tuning. We demonstrate the effectiveness of our method through competitive results in the CVPR 2nd MMFM Challenge, highlighting that carefully designed lightweight engineering can outperform expensive and complicated modeling approaches. All of our scripts, deployment steps, and evaluation results can be accessed in https://github.com/leloykun/MMFM-Challenge
title Multimodal Structured Generation: CVPR's 2nd MMFM Challenge Technical Report
topic Computer Vision and Pattern Recognition
Computation and Language
url https://arxiv.org/abs/2406.11403