Search papers, labs, and topics across Lattice.
4
0
6
2
Transforming audio captioning from a passive task into an adaptive, evidence-driven process could redefine how we approach fine-grained audio understanding.
Compositional zero-shot singing-and-dancing generation is now possible, allowing for unprecedented flexibility in video creation from audio and visual prompts.
Fine-grained audio captioning just got a major upgrade鈥擜udioMap achieves state-of-the-art results by redefining how we reward temporal accuracy and descriptive richness in audio events.
Unified audio generation just got a major upgrade鈥擲onicWeave's innovative routing mechanism boosts compositional quality and expert specialization, outperforming traditional models.
