Search papers, labs, and topics across Lattice.
4
0
6
5
LLMs show significant vulnerability to logical fallacies, with distinct profiles of resilience that could inform future model training strategies.
Aesthetics-guided training enables LeVo 2 to generate songs that not only sound good but also maintain coherence and detail, outperforming existing models.
FineCombo-TTS achieves unprecedented precision in speech synthesis by seamlessly integrating text descriptions with reference speech, allowing for fine-grained control over acoustic attributes.
Achieving state-of-the-art low-bitrate performance with a 4x reduction in codebook size, self-guidance revolutionizes neural audio coding without sacrificing fidelity.
