Search papers, labs, and topics across Lattice.
3
0
5
Forget representational differences - the secret to better feed-forward 3D scene modeling lies in tackling five core design problems.
Swap out slow, one-token-at-a-time generation in VLMs for a 6x speed boost, without sacrificing quality, using a surprisingly simple direct conversion to block-diffusion decoding.
Generating 3D scenes with diffusion models just got a whole lot more consistent across views, thanks to a new 3D-native approach that skips the 2D latent space bottleneck.
