ChatImage renders LLM answers as images, then uses visual grounding to place clickable hotspots on rendered regions for interactive follow-up.
Adding conditional control to text-to-image diffusion models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
ChatImage: Navigating Long-Form LLM Answers through Interactive Images
ChatImage renders LLM answers as images, then uses visual grounding to place clickable hotspots on rendered regions for interactive follow-up.