Autoregressive latent diffusion for 3D molecule generation

• URL: http://arxiv.org/abs/2607.09277v1
• Date: Fri, 10 Jul 2026 10:47:11 GMT
• Title: Autoregressive latent diffusion for 3D molecule generation
• Abstract summary: KRONOS is a latent autoregressive diffusion framework that generates molecules in the latent space of a pre-trained autoencoder.<n>Experiments on QM9 and GEOM-Drugs demonstrate that KRONOS achieves leading unconditional generation performance among autoregressive methods.
• Score: 11.599617045790517
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Three-dimensional (3D) molecule generation has been dominated by diffusion models, which achieve strong generation quality but typically require the molecular size to be specified a priori. Recent autoregressive approaches have substantially narrowed the performance gap while naturally supporting variable-length generation and conditioning on partial molecular context. However, balancing unconditional and context-conditioned generation remains challenging. We introduce KRONOS, a latent autoregressive diffusion framework that generates molecules in the latent space of a pre-trained autoencoder, jointly modeling molecular graph topology and geometry, while retaining the flexibility of autoregressive generation. We further introduce a mixed training strategy inspired by Fill-in-the Middle (FIM) paradigm, enabling both unconditional and fragment-conditioned molecular generation within a single left-to-right autoregressive model. Experiments on QM9 and GEOM-Drugs demonstrate that KRONOS achieves leading unconditional generation performance among autoregressive methods, while remaining competitive with diffusion models. Moreover, fragment-conditioned generation is achieved with negligible impact on unconditional generation performance, demonstrating that both generation paradigms can be supported within a single architecture.

Related papers

• Interpolating Discrete Diffusion Models with Controllable Resampling [49.771004594828405]
  Masked diffusion models suffer from irreversible errors due to early unmasking.<n>Uniform diffusion models, despite enabling self-correction, often yield low-quality samples.<n>We introduce Interpolating Discrete Diffusion Model, that improves diffusion by reducing dependence on intermediate latent states.
  arXiv  Detail & Related papers  (2026-04-19T07:55:57Z)
• CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular Generation [14.125369423416275]
  We propose CAGenMol, a condition-aware discrete diffusion framework over molecular sequences.<n>By coupling discrete diffusion with reinforcement learning, the model aligns the generation trajectory with non-differentiable objectives.<n> Experiments on structure-conditioned, property-conditioned, and dual-conditioned benchmarks demonstrate consistent improvements.
  arXiv  Detail & Related papers  (2026-04-13T13:49:23Z)
• Equivariant Asynchronous Diffusion: An Adaptive Denoising Schedule for Accelerated Molecular Conformation Generation [11.728955527605747]
  We introduce Equivariant Asynchronous Diffusion (EAD) to overcome these limitations.<n>EAD is a novel diffusion model that combines the strengths of both approaches.<n>We propose a dynamic scheduling mechanism to adaptively determine the denoising timestep.
  arXiv  Detail & Related papers  (2026-03-10T16:05:39Z)
• FlowMol3: Flow Matching for 3D De Novo Small-Molecule Generation [0.0]
  FlowMol3 is an open-source, multi-modal flow matching model that advances the state of the art for all-atom, small-molecule generation.<n>Our results highlight simple, transferable strategies for improving the stability and quality of diffusion- and flow-based molecular generative models.
  arXiv  Detail & Related papers  (2025-08-18T05:13:27Z)
• Constrained Discrete Diffusion [61.81569616239755]
  This paper introduces Constrained Discrete Diffusion (CDD), a novel integration of differentiable constraint optimization within the diffusion process.<n>CDD directly imposes constraints into the discrete diffusion sampling process, resulting in a training-free and effective approach.
  arXiv  Detail & Related papers  (2025-03-12T19:48:12Z)
• 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)
• Energy-Based Diffusion Language Models for Text Generation [126.23425882687195]
  Energy-based Diffusion Language Model (EDLM) is an energy-based model operating at the full sequence level for each diffusion step.<n>Our framework offers a 1.3$times$ sampling speedup over existing diffusion models.
  arXiv  Detail & Related papers  (2024-10-28T17:25:56Z)
• Geometric Representation Condition Improves Equivariant Molecule Generation [24.404588237915732]
  We introduce a general framework to improve molecular generative models by integrating geometric representation conditions with provable theoretical guarantees.<n>We decompose the generation process into two stages: first, generating an informative geometric representation; second, generating a molecule conditioned on the representation.<n>We observe significant quality improvements in unconditional molecule generation on the widely used QM9 and GEOM-DRUG datasets.
  arXiv  Detail & Related papers  (2024-10-04T17:57:35Z)
• LDMol: A Text-to-Molecule Diffusion Model with Structurally Informative Latent Space Surpasses AR Models [55.5427001668863]
  We present a novel latent diffusion model dubbed LDMol for text-conditioned molecule generation.<n> Experiments show that LDMol outperforms the existing autoregressive baselines on the text-to-molecule generation benchmark.<n>We show that LDMol can be applied to downstream tasks such as molecule-to-text retrieval and text-guided molecule editing.
  arXiv  Detail & Related papers  (2024-05-28T04:59:13Z)
• AUTODIFF: Autoregressive Diffusion Modeling for Structure-based Drug Design [16.946648071157618]
  We propose a diffusion-based fragment-wise autoregressive generation model for structure-based drug design (SBDD) We design a novel molecule assembly strategy named conformal motif that preserves the conformation of local structures of molecules first. We then encode the interaction of the protein-ligand complex with an SE(3)-equivariant convolutional network and generate molecules motif-by-motif with diffusion modeling.
  arXiv  Detail & Related papers  (2024-04-02T14:44:02Z)
• Learning Neural Generative Dynamics for Molecular Conformation Generation [89.03173504444415]
  We study how to generate molecule conformations (textiti.e., 3D structures) from a molecular graph. We propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph.
  arXiv  Detail & Related papers  (2021-02-20T03:17:58Z)

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.