Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
2
0
3
5
End-to-end learning of temporally predictable latent spaces for world models unlocks superior future scene understanding without the need for separate representation and prediction training stages.
By predicting future scene structure in the feature space of a frozen vision foundation model before rendering pixels, Re2Pix achieves state-of-the-art video prediction with improved temporal consistency and perceptual quality.