Search papers, labs, and topics across Lattice.
Affiliation:
4
23
8
34
LVLMs can be trained to actively mentalize spatial scenes from novel viewpoints, boosting their reasoning accuracy by up to 20% on complex tasks.
A 260M-parameter looped diffusion model achieves performance surpassing a 6.5x larger non-looped counterpart with significantly less inference compute.
HPSD enables TI2V models to internalize high-quality visual cues, resulting in a remarkable boost in text-to-video performance while simultaneously enhancing image-to-video generation.
Ditch the clunky pipelines: SongGen generates complete songs from text in a single pass, offering unprecedented control over musical elements and voice cloning.
