Search papers, labs, and topics across Lattice.
5
0
10
4
Visual grounding can now be achieved at flash speed with precise localization by treating it as parallel evidence extraction, not sequential generation.
Massive 33B video diffusion models can run 3.5x faster than real time by replacing VAE decode-reencode cycles with direct latent-to-latent resolution transfers and automated kernel synthesis.
Unlock the full potential of your pretrained video diffusion models with a surprisingly simple four-stage post-training framework that drastically improves visual quality, temporal coherence, and instruction following.
