Search papers, labs, and topics across Lattice.
3
0
7
15
CMAM revolutionizes text-based person retrieval by achieving granularity-aware matching that significantly outperforms state-of-the-art methods across diverse query levels.
By harnessing clean latent features, SharpMoE dramatically improves resource allocation to salient tokens, overcoming a key limitation in diffusion MoE architectures.
A novel graph-based dataset pruning method achieves over 40% faster training on ImageNet-1k while maintaining accuracy, challenging the status quo of sample selection.
