Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.20161v1</id>\n    <title>Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device</title>\n    <updated>2026-02-23T18:59:58Z</updated>\n    <link href='https://arxiv.org/abs/2602.20161v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.20161v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Unified multimodal models can both understand and generate visual content within a single architecture. Existing models, however, remain data-hungry and too heavy for deployment on edge devices. We present Mobile-O, a compact vision-language-diffusion model that brings unified multimodal intelligence to a mobile device. Its core module, the Mobile Conditioning Projector (MCP), fuses vision-language features with a diffusion generator using depthwise-separable convolutions and layerwise alignment. This design enables efficient cross-modal conditioning with minimal computational cost. Trained on only a few million samples and post-trained in a novel quadruplet format (generation prompt, image, question, answer), Mobile-O jointly enhances both visual understanding and generation capabilities. Despite its efficiency, Mobile-O attains competitive or superior performance compared to other unified models, achieving 74% on GenEval and outperforming Show-O and JanusFlow by 5% and 11%, while running 6x and 11x faster, respectively. For visual understanding, Mobile-O surpasses them by 15.3% and 5.1% averaged across seven benchmarks. Running in only ~3s per 512x512 image on an iPhone, Mobile-O establishes the first practical framework for real-time unified multimodal understanding and generation on edge devices. We hope Mobile-O will ease future research in real-time unified multimodal intelligence running entirely on-device with no cloud dependency. Our code, models, datasets, and mobile application are publicly available at https://amshaker.github.io/Mobile-O/</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-23T18:59:58Z</published>\n    <arxiv:comment>Project page: https://amshaker.github.io/Mobile-O/</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Abdelrahman Shaker</name>\n    </author>\n    <author>\n      <name>Ahmed Heakl</name>\n    </author>\n    <author>\n      <name>Jaseel Muhammad</name>\n    </author>\n    <author>\n      <name>Ritesh Thawkar</name>\n    </author>\n    <author>\n      <name>Omkar Thawakar</name>\n    </author>\n    <author>\n      <name>Senmao Li</name>\n    </author>\n    <author>\n      <name>Hisham Cholakkal</name>\n    </author>\n    <author>\n      <name>Ian Reid</name>\n    </author>\n    <author>\n      <name>Eric P. Xing</name>\n    </author>\n    <author>\n      <name>Salman Khan</name>\n    </author>\n    <author>\n      <name>Fahad Shahbaz Khan</name>\n    </author>\n  </entry>"
}