Search papers, labs, and topics across Lattice.
Tencent
3
0
4
BAMU achieves a remarkable MOS improvement in speech quality by dynamically allocating quantization resources based on frame complexity, outperforming traditional fixed-depth codecs.
SketchSong achieves superior song coherence and richness by explicitly planning arrangements before audio generation, outperforming strong post-trained models without extra optimization.
Generate high-fidelity 3D avatars in seconds, not minutes, by directly mapping multi-modal prompts to 3D representations using a dual diffusion model trained on a new large-scale dataset.
