Search papers, labs, and topics across Lattice.
3
0
4
1
Tactus achieves state-of-the-art object recognition from pressure data alone, outperforming traditional methods without a trained classifier head.
Structural design of the corpus, not its size, dictates what attributes a contrastive audio embedding can effectively encode.
Aligning audio with a frozen vision-language model enables seamless audio-image retrieval without any paired training data, revolutionizing multimodal search capabilities.
