Saved in:
Bibliographic Details
Main Authors: Luo, Yinyi, Wang, Wenwen, Bai, Hayes, Zhu, Hongyu, Chen, Hao, He, Pan, Savvides, Marios, Li, Sharon, Wang, Jindong
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.10784
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914581203386368
author Luo, Yinyi
Wang, Wenwen
Bai, Hayes
Zhu, Hongyu
Chen, Hao
He, Pan
Savvides, Marios
Li, Sharon
Wang, Jindong
author_facet Luo, Yinyi
Wang, Wenwen
Bai, Hayes
Zhu, Hongyu
Chen, Hao
He, Pan
Savvides, Marios
Li, Sharon
Wang, Jindong
contents Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.
format Preprint
id arxiv_https___arxiv_org_abs_2604_10784
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Luo, Yinyi
Wang, Wenwen
Bai, Hayes
Zhu, Hongyu
Chen, Hao
He, Pan
Savvides, Marios
Li, Sharon
Wang, Jindong
Artificial Intelligence
Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. In this paper, we present TorchUMM, the first unified codebase for comprehensive evaluation, analysis, and post-training across diverse UMM backbones, tasks, and datasets. TorchUMM supports a broad spectrum of models covering a wide range of scales and design paradigms. Our benchmark encompasses three core task dimensions: multimodal understanding, generation, and editing, and integrates both established and novel datasets to evaluate perception, reasoning, compositionality, and instruction-following abilities. By providing a unified interface and standardized evaluation protocols, TorchUMM enables fair and reproducible comparisons across heterogeneous models and fosters deeper insights into their strengths and limitations, facilitating the development of more capable unified multimodal systems. Code is available at: https://github.com/AIFrontierLab/TorchUMM.
title TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
topic Artificial Intelligence
url https://arxiv.org/abs/2604.10784