The rapid advancement of multi-modal language models (MLLMs) like GPT-4o has propelled the development of Omni language models, designed to process and proactively respond to continuous streams of multi-modal data. Despite their potential, evaluating their real-world interactive capabilities in streaming video contexts remains a formidable challenge. In this work, we introduce OmniMMI, a comprehensive multi-modal interaction benchmark tailored for OmniLLMs in streaming video contexts. OmniMMI encompasses over 1,121 videos and 2,290 questions, addressing two critical yet underexplored challenges in existing video benchmarks: streaming video understanding and proactive reasoning, across six distinct subtasks. Moreover, we propose a novel framework, Multi-modal Multiplexing Modeling (M4), designed to enable an inference-efficient streaming model that can see, listen while generating.
View on arXiv@article{wang2025_2503.22952,
title={ OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts },
author={ Yuxuan Wang and Yueqian Wang and Bo Chen and Tong Wu and Dongyan Zhao and Zilong Zheng },
journal={arXiv preprint arXiv:2503.22952},
year={ 2025 }
}