MOSES

Molecular Sets (MOSES): A benchmarking platform for molecular generation models Deep generative models are rapidly becoming popular for the discovery of new molecules and materials. Such models learn on a large collection of molecular structures and produce novel compounds. In this work, we introduce Molecular Sets (MO

Papers using MOSES (9)

HybridMolGen: a unified framework for goal-directed molecular generation via multi-objective reinforcement learning2026Design and Research of a Dual-Target Drug Molecular Generation Model Based on Reinforcement Learning2026MolHIT: Advancing Molecular-Graph Generation with Hierarchical Discrete Diffusion Models2026TSSR: Two-Stage Swap-Reward-Driven Reinforcement Learning for Character-Level SMILES Generation2026Graph VQ-Transformer (GVT): Fast and Accurate Molecular Generation via High-Fidelity Discrete Latents2025ReACT-Drug: Reaction-Template Guided Reinforcement Learning for de novo Drug Design2025STAR-VAE: Latent Variable Transformers for Scalable and Controllable Molecular Generation2025Discrete Bayesian Sample Inference for Graph Generation2025Probabilistic Generative Transformer Language models for Generative Design of Molecules2022 · 2 cites