Image editing models fail zero-shot visual planning on abstract mazes and queen puzzles but generalize after finetuning, yet still cannot match human zero-shot efficiency.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , month =
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.
citing papers explorer
-
Probing Visual Planning in Image Editing Models
Image editing models fail zero-shot visual planning on abstract mazes and queen puzzles but generalize after finetuning, yet still cannot match human zero-shot efficiency.
-
Analogical Trajectory Transfer
A method transfers trajectories across 3D scenes by clustering objects, predicting hierarchical smooth maps from foundation model features, assembling them combinatorially, and refining for coherence.