On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “logP”

Mol-CycleGAN - a generative model for molecular optimizationcs.LG

Mol-CycleGAN generates optimized molecules with similar structure.

problem Designing molecules with desired properties is challenging.

method CycleGAN-based model that generates optimized compounds with high structural similarity.

result Significantly outperforms previous results in optimizing penalized logP of drug-like molecules.

molecular optimization CycleGAN drug design logP structural similarity

2019-02-06abs ↗pdf ↗

Uncertainty quantification of molecular property prediction with Bayesian neural networkscs.LG

Bayesian neural networks quantify uncertainty in molecular property predictions.

problem Uncertainty in molecular property predictions due to limited data quality and quantity.

method Bayesian neural networks to decompose and quantify model- and data-driven uncertainties.

result Data noise significantly affects data-driven uncertainties in molecular property predictions.

Bayesian neural networks molecular property prediction uncertainty quantification logP predictions data-driven uncertainties

2019-03-20abs ↗pdf ↗

CORE: Automatic Molecule Optimization Using Copy & Refine Strategycs.LG

CORE optimizes molecules by copying or generating substructures, improving accuracy.

problem Inaccurate substructure prediction in molecule optimization.

method Copy & Refine (CORE) strategy combining scaffolding tree generation and adversarial training.

result Significant improvement in various molecule optimization metrics.

molecule optimization substructure prediction adversarial training scaffolding tree CORE

2019-11-23abs ↗pdf ↗

Probabilistic hypergraph grammars for efficient molecular optimizationstat.ML

Efficient molecular optimization using probabilistic hypergraph grammars and reinforcement learning.

problem Optimizing molecular structures for better performance in various benchmarks.

method Inferred a hypergraph replacement grammar from ChEMBL, used conditional priors for policy model, and applied a modified policy gradient algorithm.

result The approach results in a molecular distribution closer to the training set than using equal or unconditional priors.

molecular optimization reinforcement learning hypergraph grammars conditional priors policy gradient

2019-06-05abs ↗pdf ↗

Fréchet ChemNet Distance: A metric for generative models for molecules in drug discoverycs.LG

The new wave of successful generative models in machine learning has increased the interest in deep learning driven de novo drug design. However, assessing the performance of such generative models is notoriously difficult. Metrics that are typically used to assess the performance of such generative models are the perc…

2018-03-26abs ↗pdf ↗

Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimizationcs.LG

Active-GRPO improves molecular optimization by actively deciding when to imitate or self-improve.

problem Training robust and efficient molecular optimization models with large language models.

method Active-GRPO combines imitation and reinforcement learning, upgrading references and policies dynamically.

result Improves molecular optimization performance, achieving statistically significant gains.

molecular optimization large language models active reasoning reinforcement learning imitation

2026-07-01abs ↗pdf ↗