Search papers, labs, and topics across Lattice.
Affiliation:
3
0
3
Video diffusion models hallucinate rich scene completions but inevitably drift; anchoring their appearance priors directly inside a 3D geometric latent space eliminates sequential inconsistency and slashes trajectory error by 32%.
Underwater reconstruction just got a major upgrade, with AquaFlow slashing localization error by over 13% while enhancing image quality.
MemoryWAM achieves superior performance in robotic manipulation tasks by efficiently leveraging both short-term and long-term memory without sacrificing computational efficiency.
