Search papers, labs, and topics across Lattice.
2
0
4
0
Training-free video editing no longer requires fragmented, task-specific pipelines: unified attention-space control shatters prior zero-shot accuracy records on FiVE by nearly 20 points across both instruction- and subject-driven edits.
ELSA3D outperforms existing unified 3D models by halving computational costs while enhancing cross-modal reasoning precision.
