Search papers, labs, and topics across Lattice.
3
0
5
Speed up 3D Gaussian Splatting training by over 70% without sacrificing reconstruction quality through a novel frequency-staged approach.
LeanGRPO achieves up to 1.83x speedup in diffusion RL without sacrificing optimization quality by eliminating redundant computations.
Zellige redefines sequence placement for DiT training, achieving up to 1.54x faster performance than existing methods while optimizing resource utilization.
