TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
Yinyi Luo, Wenwen Wang, Hayes Bai, Hongyu Zhu, Hao Chen, Pan He, Marios Savvides, Sharon Li, Jindong Wang
Feedback
Why It Matters
This work is significant as it facilitates fair comparisons across various multimodal models, promoting reproducibility and deeper understanding of their capabilities and limitations, which is crucial for advancing the field.
Contributions
- Development of a unified codebase for multimodal model evaluation and analysis.
Insights
- The integration of both established and novel datasets allows for a comprehensive evaluation of multimodal models across different tasks.
Limitations
- The codebase may not cover all existing multimodal architectures, potentially limiting its applicability.
Tags
- benchmark
- evaluation
- infra
- multimodal
Abstract
arXiv:2604.10784v1 Announce Type: new Abstract: 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.