Search papers, labs, and topics across Lattice.
3
0
6
Latent spatial memory can accelerate video generation by over 10 times while dramatically reducing memory usage, revolutionizing how we model dynamic scenes.
SkillOpt transforms agent skill development into a reproducible optimization process, achieving state-of-the-art results by treating skills as trainable parameters.
Text-to-video models can now learn geometrically consistent world dynamics via reinforcement learning, without expensive architectural changes.
