Paper Detail
Yabo Zhang, Kunchang Li, Dewei Zhou, Xinyu Huang, Xun Wang
While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems from the structural separation of images and text in current paradigms, which forces models to bridge difficult long-range dependencies to match descriptions with visual targets. To address these challenges, we propose \texttt{I}mages i\texttt{N} \texttt{SE}n\texttt{T}ences (\textit{a.k.a}, INSET), a unified generation model that seamlessly embeds images as native vocabulary within textual instructions. By positioning visual features directly at their corresponding semantic slots, INSET leverages the contextual locality of transformers for precise object binding, effectively treating images as dense, expressive language tokens. Furthermore, we introduce a scalable data engine that synthesizes 15M high-quality interleaved samples from standard image and video datasets, utilizing VLMs and LLMs to construct rich, long-horizon sequences. Evaluation results on InterleaveBench demonstrate that INSET significantly outperforms state-of-the-art methods in multi-image consistency and text alignment, with performance gaps widening as input complexity increases. Beyond standard generation, our approach inherently extends to multimodal image editing, integrating visual content as part of the instruction to facilitate highly expressive and creative visual manipulations.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@article{zhang2026images,
title = {Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation},
author = {Yabo Zhang and Kunchang Li and Dewei Zhou and Xinyu Huang and Xun Wang},
year = {2026},
abstract = {While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance under complex interleaved instructions. This limitation stems from the structural separation of images and text in current paradigms, which forces models to bridge difficult long-range dependencies to match descriptions with visual targets. To address these challenges, we propose \textbackslash{}texttt\{I\}mages i\textbackslash{}texttt\{N\} \textbackslash{}texttt\{SE\}n\textbackslash{}},
url = {https://arxiv.org/abs/2605.12305},
keywords = {cs.CV},
eprint = {2605.12305},
archiveprefix = {arXiv},
}
{}