Firehose

23 JUL 2026 · Paper

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text

This paper develops a framework to evaluate spatial cognition in image-generation models by asking them to draw or mark answers in a visual space, rather than relying on text-based inputs. Practitioners might care about this research to better understand how image-generation models think spatially and to improve their performance on tasks that require spatial reasoning.

image-generation models spatial cognition visual benchmarks pixel space protocolized evaluation

Browse by tag

Show, Don't Tell: Evaluating Spatial Cognition in Generative Pixels Rather Than LLM Text