MolWorld: Molecule World Models for Actionable Molecular Optimization
cs.LG, cs.AI
Submitted: 2026-05-09
Updated: 2026-10-01
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- Augmented Memory: Capitalizing on Experience Replay to Accelerate De Novo Molecular Design
- World Models
- Mastering Diverse Domains through World Models
- GAIA-1: A Generative World Model for Autonomous Driving
- Hierarchical Graph-to-Graph Translation for Molecules
- GenMol: A Drug Discovery Generalist with Discrete Diffusion
- Latent Bayesian Optimization via Autoregressive Normalizing Flows
- Learning to Model the World with Language
- GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
- Retrieval-based Controllable Molecule Generation
- Learning Interactive Real-World Simulators
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks