DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
arXiv preprint arXiv:2208.09016 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Contrastive KERMT pretraining on molecular graphs yields 7.6-9.9% average gains over KERMT baseline on Biogen, ExpansionRX, and ChEMBL-MT ADME endpoints via a single probabilistic latent-variable objective and task-specific GNN heads.
citing papers explorer
-
DGLD: Domain-Gated Latent Diffusion for the Discovery of Novel Energetic Materials
DGLD applies domain-gated latent diffusion with label-quality gating and multi-task guidance to discover 12 novel energetic material leads validated by DFT, outperforming SMILES-LSTM, SELFIES-GA, and REINVENT baselines in novelty and on-target performance.
-
Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction
Contrastive KERMT pretraining on molecular graphs yields 7.6-9.9% average gains over KERMT baseline on Biogen, ExpansionRX, and ChEMBL-MT ADME endpoints via a single probabilistic latent-variable objective and task-specific GNN heads.