Game2Real-Bench links toy-game scores to real visual reasoning
Across 25 vision-language models, game and real scores correlate at 0.935; constraint reasoning rose in one-shot transfer.
1 stories, newest first · one card per story
Across 25 vision-language models, game and real scores correlate at 0.935; constraint reasoning rose in one-shot transfer.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views