Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
4
State-of-the-art text-to-image models, despite photorealism, still exhibit pervasive world-consistency failures that existing metrics miss.
Latent spatial memory can accelerate video generation by over 10 times while dramatically reducing memory usage, revolutionizing how we model dynamic scenes.
Unlock geometry-precise 3D generation by directly conditioning diffusion models on readily available point cloud priors, outperforming existing image- or text-conditioned methods.
Generative video models can now simulate a continuously evolving world, even when objects are out of sight, thanks to a new framework that maintains persistent global state.
