Search papers, labs, and topics across Lattice.
2
0
5
SF-Mamba achieves state-of-the-art vision performance and improved throughput by rethinking Mamba's scan operation with bidirectional patch swapping and optimized GPU parallelism.
MMHNet proves you can train a video-to-audio model on short clips and have it generalize to generate coherent audio for videos over 5 minutes long.
