FlashMol: High-Quality Molecule Generation in as Few as Four Steps

• URL: http://arxiv.org/abs/2605.07020v1
• Date: Thu, 07 May 2026 23:04:24 GMT
• Title: FlashMol: High-Quality Molecule Generation in as Few as Four Steps
• Abstract summary: FlashMol is an ultra-fast molecule generative model producing high-quality molecular conformations in as few as 4 steps.<n>Experiments on QM9 and GEOM-DRUG datasets demonstrate that FlashMol matches and even surpasses the original 1000-step teacher.
• Score: 33.25994871049577
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Generating chemically valid 3D molecular conformations is critical for computational drug discovery. Classical diffusion-based models like GeoLDM perform well but require hundreds of steps, making large-scale in silico screening impractical. Recent efforts on few-step molecular generation have accelerated this process to 12-50 steps, but they often largely sacrifice sample stability. In this work, we present FlashMol, an ultra-fast molecule generative model producing high-quality molecular conformations in as few as 4 steps. To achieve this, we adapt distribution matching distillation (DMD) - a reverse KL-divergence minimization objective - to the molecular domain for effective distillation. Considering the local minimization behavior of DMD, we respace the molecule generation timesteps, providing the generator with much better initialization and enables effective distillation. Additionally, to mitigate the mode-seeking behavior of DMD and improve diversity, we further regularize it with a Jensen-Shannon divergence term, which incorporates the mean-seeking behavior of the forward KL divergence. Extensive experiments on QM9 and GEOM-DRUG datasets demonstrate that FlashMol matches and even surpasses the original 1000-step teacher, achieving up to 250$\times$ acceleration in sampling speed while maintaining high molecular quality.

Related papers

• Towards Unified and Lossless Latent Space for 3D Molecular Latent Diffusion Modeling [90.23688195918432]
  3D molecule generation is crucial for drug discovery and material science.<n>Existing approaches typically maintain separate latent spaces for invariant and equivariant modalities.<n>We propose textbfUAE-3D, a multi-modal VAE that compresses 3D molecules into latent sequences from a unified latent space.
  arXiv  Detail & Related papers  (2025-03-19T08:56:13Z)
• Straight-Line Diffusion Model for Efficient 3D Molecular Generation [25.63489191042975]
  We introduce a novel Straight-Line Diffusion Model (SLDM) to tackle this problem.<n>The proposed process aligns well with the noise sensitivity characteristic of molecular structures and uniformly distributes reconstruction effort across the generative process.<n>SLDM achieves state-of-the-art performance on 3D molecule generation benchmarks, delivering a 100-fold improvement in sampling efficiency.
  arXiv  Detail & Related papers  (2025-03-04T13:23:58Z)
• Conditional Synthesis of 3D Molecules with Time Correction Sampler [58.0834973489875]
  Time-Aware Conditional Synthesis (TACS) is a novel approach to conditional generation on diffusion models. It integrates adaptively controlled plug-and-play "online" guidance into a diffusion model, driving samples toward the desired properties.
  arXiv  Detail & Related papers  (2024-11-01T12:59:25Z)
• EM Distillation for One-step Diffusion Models [65.57766773137068]
  We propose a maximum likelihood-based approach that distills a diffusion model to a one-step generator model with minimal loss of quality.<n>We develop a reparametrized sampling scheme and a noise cancellation technique that together stabilizes the distillation process.
  arXiv  Detail & Related papers  (2024-05-27T05:55:22Z)
• Data-Efficient Molecular Generation with Hierarchical Textual Inversion [48.816943690420224]
  We introduce Hierarchical textual Inversion for Molecular generation (HI-Mol), a novel data-efficient molecular generation method. HI-Mol is inspired by the importance of hierarchical information, e.g., both coarse- and fine-grained features, in understanding the molecule distribution. Compared to the conventional textual inversion method in the image domain using a single-level token embedding, our multi-level token embeddings allow the model to effectively learn the underlying low-shot molecule distribution.
  arXiv  Detail & Related papers  (2024-05-05T08:35:23Z)
• Accelerating the Generation of Molecular Conformations with Progressive Distillation of Equivariant Latent Diffusion Models [0.0]
  We introduce Equivariant Latent Progressive Distillation, a fast sampling algorithm that preserves geometric equivariance and accelerates generation from latent diffusion models. Our experiments demonstrate up to 7.5x gains in sampling speed with limited degradation in molecular stability.
  arXiv  Detail & Related papers  (2024-04-21T00:04:38Z)
• Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics [24.13304926093212]
  We present Timewarp, an enhanced sampling method which uses a normalising flow as a proposal distribution in a Markov chain Monte Carlo method. The flow is trained offline on MD trajectories and learns to make large steps in time, simulating the molecular dynamics of $105 - 106:textrmfs$.
  arXiv  Detail & Related papers  (2023-02-02T15:48:39Z)
• Exploring Chemical Space with Score-based Out-of-distribution Generation [57.15855198512551]
  We propose a score-based diffusion scheme that incorporates out-of-distribution control in the generative differential equation (SDE) Since some novel molecules may not meet the basic requirements of real-world drugs, MOOD performs conditional generation by utilizing the gradients from a property predictor. We experimentally validate that MOOD is able to explore the chemical space beyond the training distribution, generating molecules that outscore ones found with existing methods, and even the top 0.01% of the original training pool.
  arXiv  Detail & Related papers  (2022-06-06T06:17:11Z)
• Pseudo Numerical Methods for Diffusion Models on Manifolds [77.40343577960712]
  Denoising Diffusion Probabilistic Models (DDPMs) can generate high-quality samples such as image and audio samples. DDPMs require hundreds to thousands of iterations to produce final samples. We propose pseudo numerical methods for diffusion models (PNDMs) PNDMs can generate higher quality synthetic images with only 50 steps compared with 1000-step DDIMs (20x speedup)
  arXiv  Detail & Related papers  (2022-02-20T10:37:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.