Search papers, labs, and topics across Lattice.
3
0
7
WorldCache achieves up to 3.7x speedups in diffusion-based world models by intelligently caching and selectively recomputing tokens, making interactive and long-horizon rollouts far more practical.
An animation framework trained on just two characters can generalize to animating scenes with many more, without sacrificing single-character performance.
Forget monolithic adapters: a hierarchical "expert forest" leverages semantic relationships between tasks to achieve state-of-the-art performance in class-incremental learning.
