Spatial Harness grounds VLM spatial reasoning in physics-engine states
On MindCube it raises Qwen3.5-27B from 52.70% to 71.14%, and to 98.25% when poses are annotated.
1 stories, newest first · one card per story
On MindCube it raises Qwen3.5-27B from 52.70% to 71.14%, and to 98.25% when poses are annotated.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views