LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
Smiles, a chemical language and information system
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
Topology-aware large graph representations of polymer chains combined with masked pretraining on unlabeled data reduce prediction error for glass transition temperature by 5.1% compared to repeat-unit baselines.
citing papers explorer
-
Toward Better Geometric Representations for Molecule Generative Models
LENSEs improves representation-conditioned molecule generation by jointly training a multi-level representation head, perceptual loss, and REPA alignment on pretrained encoders, yielding 97.28% validity and 98.51% stability on GEOM-DRUG.
-
It's All Connected: Topology-Aware Structural Graph Encoding Improves Performance on Polymer Prediction
Topology-aware large graph representations of polymer chains combined with masked pretraining on unlabeled data reduce prediction error for glass transition temperature by 5.1% compared to repeat-unit baselines.