Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
4
0
6
VLMs can be taught to *use* latent geometry by training them to read continuous geometric tokens, rather than just reconstructing geometry from RGB.
MAG leverages abundant unlabeled multi-modal data to boost few-shot learning performance, achieving significant gains in label-scarce environments.
Pathology-specific evaluation metrics reveal that increasing synthetic data diversity boosts segmentation model performance more than visual fidelity does.