# Vision-Language DiffMean Axis Ablation

Whether multimodal training changes how a model reasons over text alone had been supported mainly by behavior. Across 10 multimodal configurations from 6 model families, this work builds a vision–language direction and removes each hidden state's projection onto it at inference; in Chameleon-7B, BBH navigate drops while boolean expressions stay largely intact, a double dissociation. The effect is direction-specific and layer-localized, and extends to mental-simulation tasks such as mental rotation, paper folding and perspective taking.

Whether multimodal training changes how a model reasons over text alone had been supported mainly by behavior. Across 10 multimodal configurations from 6 model families, this work builds a vision–language direction and removes each hidden state's projection onto it at inference; in Chameleon-7B, BBH navigate drops while boolean expressions stay largely intact, a double dissociation. The effect is direction-specific and layer-localized, and extends to mental-simulation tasks such as mental rotation, paper folding and perspective taking.