#artificial intelligence
May 2025
VisualSphinx: Large-Scale Synthetic Vision Logic Puzzles for RL
A rule-to-image synthesis pipeline that extracts and expands puzzle rules from seed questions and generates executable rendering programs for puzzle assembly to tackle the challenge of image synthesis with grounded answers is proposed.
Yichen Feng, Zhangchen Xu, Feng-Qing Jiang et al.
· arXiv.org · 15 citations
· ⚡1