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 2verdicts
UNVERDICTED 2representative citing papers
MMBench-Live introduces an automated multi-agent pipeline and distribution-consistent update strategy to create a continuously evolving multimodal benchmark with 5.9K new instances at low cost.
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.
-
MMBench-Live: A Continuously Evolving Benchmark for Multimodal Models
MMBench-Live introduces an automated multi-agent pipeline and distribution-consistent update strategy to create a continuously evolving multimodal benchmark with 5.9K new instances at low cost.