Search papers, labs, and topics across Lattice.
5
0
7
0
OmniUE achieves an unprecedented 83.7% improvement in visual-interactive benchmarks, setting a new standard for multimodal embedding performance.
ProRetrieval outperforms state-of-the-art models by synthesizing executable retrieval programs that seamlessly combine structured and unstructured data queries.
A single grid image can streamline document-level visual retrieval, slashing storage needs by over 10x while boosting retrieval performance.
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.
