MammothModa: Multi-Modal Large Language Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: She, Qi, Pan, Junwen, Wan, Xin, Zhang, Rui, Lu, Dawei, Huang, Kai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914849252966400
author She, Qi
Pan, Junwen
Wan, Xin
Zhang, Rui
Lu, Dawei
Huang, Kai
author_facet She, Qi
Pan, Junwen
Wan, Xin
Zhang, Rui
Lu, Dawei
Huang, Kai
contents In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline. We focus on three key design insights: (i) Integrating Visual Capabilities while Maintaining Complex Language Understanding: In addition to the vision encoder, we incorporated the Visual Attention Experts into the LLM to enhance its visual capabilities. (ii) Extending Context Window for High-Resolution and Long-Duration Visual Feature: We explore the Visual Merger Module to effectively reduce the token number of high-resolution images and incorporated frame position ids to avoid position interpolation. (iii) High-Quality Bilingual Datasets: We meticulously curated and filtered a high-quality bilingual multimodal dataset to reduce visual hallucinations. With above recipe we build MammothModa that consistently outperforms the state-of-the-art models, e.g., LLaVA-series, across main real-world visual language benchmarks without bells and whistles.
format Preprint
id arxiv_https___arxiv_org_abs_2406_18193
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle MammothModa: Multi-Modal Large Language Model
She, Qi
Pan, Junwen
Wan, Xin
Zhang, Rui
Lu, Dawei
Huang, Kai
Computer Vision and Pattern Recognition
Artificial Intelligence
In this report, we introduce MammothModa, yet another multi-modal large language model (MLLM) designed to achieve state-of-the-art performance starting from an elementary baseline. We focus on three key design insights: (i) Integrating Visual Capabilities while Maintaining Complex Language Understanding: In addition to the vision encoder, we incorporated the Visual Attention Experts into the LLM to enhance its visual capabilities. (ii) Extending Context Window for High-Resolution and Long-Duration Visual Feature: We explore the Visual Merger Module to effectively reduce the token number of high-resolution images and incorporated frame position ids to avoid position interpolation. (iii) High-Quality Bilingual Datasets: We meticulously curated and filtered a high-quality bilingual multimodal dataset to reduce visual hallucinations. With above recipe we build MammothModa that consistently outperforms the state-of-the-art models, e.g., LLaVA-series, across main real-world visual language benchmarks without bells and whistles.
title MammothModa: Multi-Modal Large Language Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2406.18193