Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.19497v1</id>\n    <title>MICON-Bench: Benchmarking and Enhancing Multi-Image Context Image Generation in Unified Multimodal Models</title>\n    <updated>2026-02-23T04:32:52Z</updated>\n    <link href='https://arxiv.org/abs/2602.19497v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.19497v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Recent advancements in Unified Multimodal Models (UMMs) have enabled remarkable image understanding and generation capabilities. However, while models like Gemini-2.5-Flash-Image show emerging abilities to reason over multiple related images, existing benchmarks rarely address the challenges of multi-image context generation, focusing mainly on text-to-image or single-image editing tasks. In this work, we introduce \\textbf{MICON-Bench}, a comprehensive benchmark covering six tasks that evaluate cross-image composition, contextual reasoning, and identity preservation. We further propose an MLLM-driven Evaluation-by-Checkpoint framework for automatic verification of semantic and visual consistency, where multimodal large language model (MLLM) serves as a verifier. Additionally, we present \\textbf{Dynamic Attention Rebalancing (DAR)}, a training-free, plug-and-play mechanism that dynamically adjusts attention during inference to enhance coherence and reduce hallucinations. Extensive experiments on various state-of-the-art open-source models demonstrate both the rigor of MICON-Bench in exposing multi-image reasoning challenges and the efficacy of DAR in improving generation quality and cross-image coherence. Github: https://github.com/Angusliuuu/MICON-Bench.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-02-23T04:32:52Z</published>\n    <arxiv:comment>CVPR2026</arxiv:comment>\n    <arxiv:primary_category term='cs.CV'/>\n    <author>\n      <name>Mingrui Wu</name>\n    </author>\n    <author>\n      <name>Hang Liu</name>\n    </author>\n    <author>\n      <name>Jiayi Ji</name>\n    </author>\n    <author>\n      <name>Xiaoshuai Sun</name>\n    </author>\n    <author>\n      <name>Rongrong Ji</name>\n    </author>\n  </entry>"
}