Benchmark
JNono-200K
An evaluation dataset for nonogram puzzle tasks in joint text-and-image generation, containing approximately 200,000 samples. It is used to evaluate cross-modal logical consistency.
Timeline (last 90 days)
Sep 30
The team released three datasets: JEdit-1M (million-scale image editing), JMaze-200K (approximately 200,000 maze samples), and JNono-200K (approximately 200,000 nonogram samples).
Unverified50%