Skip to content
GCC AI Research

Fixed-Dimensional Latent Flow for Generating Variable-Size 3D Molecules

arXiv ·

Summary

Researchers introduce Equivariant-Free Transformer-Autoencoded Latent Flow Matching (EF-TALFM), a two-stage generative framework designed to create variable-size 3D molecules using a single fixed-dimensional latent representation. This method employs an autoregressive Transformer decoder to determine molecule size and generate atom types, coordinates, and chemical states without requiring equivariant layers. EF-TALFM achieved 89.4% unique, novel, and sanitized molecules on the PCQM4Mv2 benchmark, outperforming existing models, and demonstrated higher computational throughput. Why it matters: This innovative architecture provides a practical and efficient approach for open-ended and property-directed 3D molecular design, which is crucial for advancements in drug discovery and materials science.

Get the weekly digest

Top AI stories from the GCC region, every week.

Related

Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling

arXiv ·

The paper introduces UAE-3D, a multi-modal VAE for 3D molecule generation that compresses molecules into a unified latent space, maintaining near-zero reconstruction error. This approach simplifies latent diffusion modeling by eliminating the need to handle multi-modality and equivariance separately. Experiments on GEOM-Drugs and QM9 datasets show UAE-3D establishes new benchmarks in de novo and conditional 3D molecule generation, with significant improvements in efficiency and quality.

Generative models, manifolds and symmetries: From QFT to molecules

MBZUAI ·

A DeepMind researcher presented work on incorporating symmetries into machine learning models, with applications to lattice-QCD and molecular dynamics. The work includes permutation and translation-invariant normalizing flows for free-energy estimation in molecular dynamics. They also presented U(N) and SU(N) Gauge-equivariant normalizing flows for pure Gauge simulations and its extensions to incorporate fermions in lattice-QCD. Why it matters: Applying symmetry principles to generative models could improve AI's ability to model complex physical systems relevant to materials science and other fields in the region.

Diffusion-BBO: Diffusion-Based Inverse Modeling for Online Black-Box Optimization

arXiv ·

This paper introduces Diffusion-BBO, a new online black-box optimization (BBO) framework that uses a conditional diffusion model as an inverse surrogate model. The framework employs an Uncertainty-aware Exploration (UaE) acquisition function to propose scores in the objective space for conditional sampling. The approach is shown theoretically to achieve a near-optimal solution and empirically outperforms existing online BBO baselines across 6 scientific discovery tasks.

Efficiently Approximating Equivariance in Unconstrained Models

MBZUAI ·

Ahmed Elhag, a PhD student at the University of Oxford, presented a new training procedure that approximates equivariance in unconstrained machine learning models via a multitask objective. The approach adds an equivariance loss to unconstrained models, allowing them to learn approximate symmetries without the computational cost of fully equivariant methods. Formulating equivariance as a flexible learning objective allows control over the extent of symmetry enforced, matching the performance of strictly equivariant baselines at a lower cost. Why it matters: This research from a speaker at MBZUAI balances rigorous theory and practical scalability in geometric deep learning, potentially accelerating drug discovery and design.