Search papers, labs, and topics across Lattice.
4
0
6
Turning published scientific figures back into executable Python remains a brittle frontier for top VLMs, with even frontier models routinely failing on multi-component layouts, precise axis semantics, and domain typography.
TFMat achieves a remarkable 92.04% match rate in crystal structure prediction by harnessing structured text as a control layer for flow-based generation.
CoMPASS achieves a remarkable balance, enhancing molecular predictions by intelligently integrating LLM insights only when uncertainty is high, leading to improved accuracy without sacrificing reliability.
MatRank's innovative approach to pseudo-labeling reduces prediction error by effectively utilizing unlabeled data, achieving a remarkable NMAE of 0.896.
