Atomas: Hierarchical Alignment on Molecule-Text for Unified Molecule Understanding and Generation

arXiv:2404.16880v1 Announce Type: cross
Abstract: Molecule-and-text cross-modal representation learning has emerged as a promising direction for enhancing the quality of molecular representation, thereby improving performance in various scientific fields, including drug discovery and materials science. Existing studies adopt a global alignment approach to learn the knowledge from different modalities. These global alignment approaches fail to capture fine-grained information, such as molecular fragments and their corresponding textual description, which is crucial for downstream tasks. Furthermore, it is incapable to model such …

alignment arxiv cs.ai cs.cl hierarchical q-bio.qm text type understanding