SOURCE-LINKED INTELLIGENCE

Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment

arXiv · AI, language, vision and robotics · article · Sep 2, 2026 · UTC

Current evaluations and training of multimodal models predominantly focus on multi-image tasks, largely overlooking interleaved text-image scenarios. In such multi-image tasks, text typically serves merely as task instructions, lacking deep semantic interaction with the visual content. In contrast, realworld applications like text-image co-creation, character tracking, and spatial reconstruction require constant interaction between text and images. Consequently, models must possess a deep understanding of these interleaved contexts. To bridge this gap, we introduce a novel benchmark, TIC-Bench

Read original source ↗ Open in workspace

recordType

paper

region

Global