Microsoft open-sources Phi-4-reasoning-vision-15B for compact multimodal reasoning
Microsoft just released Phi-4-reasoning-vision-15B, an open-weight 15B parameter multimodal reasoning model trained on just 200 billion multimodal tokens. It pairs a SigLIP-2 Naflex dynamic vision encoder with a mid-fusion backbone to excel at math, science, and UI screen parsing. Why it matters: it rivals much larger VLMs using a fraction of the compute.