Online fine-tuning of discrete diffusion models with complementary acquisition, CVaR shaping, density-entropy debiasing, replay, and validity control finds better molecules under fixed oracle budgets than offline fine-tuning or inference-time search.
FlashAffinity: Bridging the Accuracy- Speed Gap in Protein-Ligand Binding Affinity Prediction.bioRxiv, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
Online fine-tuning of discrete diffusion models with complementary acquisition, CVaR shaping, density-entropy debiasing, replay, and validity control finds better molecules under fixed oracle budgets than offline fine-tuning or inference-time search.