RoTA-Bench：通过交互式投影对齐评估3D空间推理

arXiv 2610.17665 · 21 人推荐 · 附代码 MAC-AutoML/RoTA-Bench。Can vision-language models turn 2D observations into 3D understanding that supports precise action? This requires inferring object geometry, anticipating the effects of rotation, and refining actions through visual feedback. We introduce RoTA-Bench to evaluate these abilities through interactive 3D-to-2D projection alignment. Given a target silhouette, a model observes a rotated object and chooses successive rotations to recover the target projection within a limited action budget. Our automated