Search papers, labs, and topics across Lattice.
3
0
5
2
Automated data curation and imbalance-aware training strategies significantly enhance LALMs' performance on culturally diverse folk music, yet deep musical understanding remains elusive.
Unlock more realistic human-machine interaction with ActorMind, a framework that enables AI to convincingly role-play via speech by reasoning about roles, scenes, and emotional cues like a human actor.
Audio-Omni can edit sound, music, and speech with a single model, rivaling specialized systems and unlocking capabilities like knowledge-augmented reasoning and zero-shot cross-lingual control.