Search papers, labs, and topics across Lattice.
2
0
5
Seedance 2.0 leapfrogs existing models by unifying multi-modal inputs (text, image, audio, video) into a single architecture for generating high-quality, longer-duration audio-video content.
Audio-specific KV cache eviction lets you compress LALMs by 40% with almost no accuracy loss, while generic methods fall apart.
