Search papers, labs, and topics across Lattice.
3
0
6
2
Eight-bit quantization allows a $1.2$-billion-parameter model to run on an $8$\,GB Raspberry Pi without sacrificing audio quality or speed.
Predicting taste from audio embeddings not only surpasses human consensus but also redefines the benchmarks for music retrieval systems.
Expertly curated data beats sheer data quantity: a small, musicologically-informed LilyPond dataset outperforms a 150x larger MIDI corpus for music understanding tasks.
