Search papers, labs, and topics across Lattice.
Affiliation:
2
3
5
6
Current TTS evaluators miss the mark, with MOS predictors focusing solely on sound quality and Audio-LLMs struggling to generalize across speech dimensions.
Frontier-level multimodal reasoning is now within reach for organizations with limited infrastructure, thanks to a 15B parameter model that rivals much larger models through clever training design, not brute force scaling.
