ChatImage: Navigating Long-Form LLM Answers through Interactive Images
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors created ChatImage, a system that turns long text answers from large language models into interactive pictures. Instead of just reading a long block of text, users can click on parts of the picture to get more details about that specific section. ChatImage organizes the text into visual pieces, arranges them, creates an image, and then uses other AI tools to find clickable spots on the picture. This helps users explore detailed answers more easily without rereading everything. The authors also tested their system with different types of visual answers like maps and infographics.
Large Language ModelsInteractive VisualizationVision GroundingLocateAnythingMiMo-VisionSAM (Segment Anything Model)Visual LayoutClickable HotspotsInfographicsBenchmarking
Authors
Wencan Jiang, Jiangning Zhang, Yong Liu
Abstract
Large Language Models (LLMs) can produce detailed answers to complex queries, but these answers are typically presented as dense linear text, which makes fine-grained inspection, navigation, and return visits difficult. We present ChatImage, a system that converts long-form LLM answers into interactive visual images. Given a textual answer, ChatImage first normalizes its content into structured visual modules, plans a visual layout, and renders a coherent image. It then applies a second grounding pass to the rendered image with vision grounding models such as LocateAnything and MiMo-Vision, with optional SAM-style mask refinement, to identify the visible regions that should support interaction. From these grounded regions, ChatImage overlays transparent clickable hotspots on the image. Each hotspot opens a detail panel and a region-scoped follow-up thread, allowing the user to inspect and query a specific part of the answer without re-reading the full response. Instead of treating planned coordinates as the final interaction geometry, ChatImage uses them as priors and grounds the interaction targets after rendering, which improves consistency between visual content and clickable regions. We release a reference implementation and introduce a 30-question benchmark covering infographic, map, and scene-based answer formats. Evaluation with configured external models reports interaction-loop completion, a strict visual-alignment gate, and a SAM-based mask-completeness diagnostic.