arXiv AI
MolWorld: Molecule World Models for Actionable Molecular Optimization
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Aug 26
MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
arXiv:2510.07289v2 Announce Type: replace Abstract: Molecular graph representation learning is widely used in chemical and biomedical research. While pre-trained 2D graph encoders have demonstrated s...
arXiv Machine Learning
Jul 22
DBMol: Design of High-Affinity, Target-Specific Small Molecules through Structure Prediction Models
arXiv:2607. 19237v1 Announce Type: new Abstract: Designing small molecule ligands that bind with high affinity to specific protein pockets is a fundamental goal in drug discovery, as small molecules constitute a major fraction of approved therapeutics.
arXiv Machine Learning
Jul 3
Do LLMs Truly Generalize in the Molecular Domain? A Perturbation-Based Analysis
arXiv:2607. 01800v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently shown promise in molecular discovery, yet a gap remains between their probabilistic nature over discrete sequential tokens and the rigid topological constraints of chemical space.
arXiv AI
Aug 5
GraphCliff: Short-Long Range Gating for Modeling Critical Activity Changes Caused by Subtle Molecular Differences
arXiv:2511. 03170v3 Announce Type: replace-cross Abstract: The quantitative structure-activity relationship assumes a smooth mapping between molecular structure and biological activity.
arXiv AI
Jul 7
Back to Basics: Improving Molecular Understanding in LLMs via SMILES-Graph Translation
arXiv:2607. 03007v1 Announce Type: cross Abstract: Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains often come without reliable structural grounding.
arXiv AI
Aug 25
Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for Molecules
Mol-JEPA is a scalable multimodal framework that learns molecular world models by using modality masking instead of suboptimal perturbations. It incorporates diverse data such as molecular structures, cellular phenotypes, binding affinities, ADMET profiles, quantum chemistry simulations, and other drug‑discovery information. Benchmarks show that the representations it learns perform strongly, highlighting the benefit of embedding biochemical context via latent‑space prediction.