MirroS finds S-Space: a manipulable spatial workspace inside multimodal models

HeyAmit_ · x · 2026-09-09

MirroS research identifies S-Space, a structured internal spatial map in multimodal models analogous to human spatial cognition. Researchers can read, manipulate, and track it during reasoning. Crucially, changing an object's spatial coordinates inside the representation systematically flips the model's spatial judgments — left becomes right, above becomes below — suggesting S-Space plays a causal role in spatial reasoning, not just an inspectable representation. Released with an interactive blog, technical report, and all experiment code.

Original post →

More from Research

Research channel →