Search papers, labs, and topics across Lattice.
2
0
6
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.
LLMs can achieve 2.5x higher throughput and 10.7x KV memory reduction in long-context reasoning by compressing the KV cache using trigonometric functions derived from pre-RoPE query/key vector distributions.
