VecMol: Vector-Field Representations for 3D Molecule Generation
This addresses a fundamental challenge in drug discovery and materials science by introducing a paradigm-shifting representation for 3D molecule generation.
The paper tackles the problem of generative modeling of 3D molecules by proposing VecMol, a framework that represents molecules as continuous vector fields to avoid issues like modality entanglement, and experiments on QM9 and GEOM-Drugs benchmarks validate its feasibility as a new direction.
Generative modeling of three-dimensional (3D) molecules is a fundamental yet challenging problem in drug discovery and materials science. Existing approaches typically represent molecules as 3D graphs and co-generate discrete atom types with continuous atomic coordinates, leading to intrinsic learning difficulties such as heterogeneous modality entanglement and geometry-chemistry coherence constraints. We propose VecMol, a paradigm-shifting framework that reimagines molecular representation by modeling 3D molecules as continuous vector fields over Euclidean space, where vectors point toward nearby atoms and implicitly encode molecular structure. The vector field is parameterized by a neural field and generated using a latent diffusion model, avoiding explicit graph generation and decoupling structure learning from discrete atom instantiation. Experiments on the QM9 and GEOM-Drugs benchmarks validate the feasibility of this novel approach, suggesting vector-field-based representations as a promising new direction for 3D molecular generation.