Search papers, labs, and topics across Lattice.
2
0
5
37
Across six diverse visual reasoning tasks including multi-view spatial reasoning and collision prediction, ReImaGin consistently outperforms both text-only reasoning and specialist vision-tool baselines, with gains of up to 25\%, demonstrating the advantage of flexible, generative visual reasoning.
Diffusion models struggle with multi-object generation not because of imbalanced concept representation, but primarily due to scene complexity and a surprising difficulty in counting, especially when training data is limited.
