Search papers, labs, and topics across Lattice.
The University of Hong Kong
2
0
4
4
Control both multi-subject identity and multi-granularity motion in video generation with DreamVideo-Omni, a framework that uses latent identity reinforcement learning to avoid identity degradation.
Achieve state-of-the-art video generation with 24% fewer tokens by adaptively allocating tokens based on video segment complexity.
