{"slug": "autoregressive-latent-diffusion-for-3d-molecule-generation", "title": "Autoregressive latent diffusion for 3D molecule generation", "summary": "Researchers introduced KRONOS, a latent autoregressive diffusion framework for 3D molecule generation that jointly models molecular graph topology and geometry in latent space. The model uses a mixed training strategy inspired by Fill-in-the-Middle to enable both unconditional and fragment-conditioned generation within a single architecture. Experiments on QM9 and GEOM-Drugs show KRONOS achieves leading unconditional generation performance among autoregressive methods while remaining competitive with diffusion models.", "body_md": "arXiv:2607.09277v1 Announce Type: new\nAbstract: 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.", "url": "https://wpnews.pro/news/autoregressive-latent-diffusion-for-3d-molecule-generation", "canonical_source": "https://www.machinebrief.com/news/autoregressive-latent-diffusion-for-3d-molecule-generation-5x2t", "published_at": "2026-07-13 04:00:00+00:00", "updated_at": "2026-07-13 04:20:37.275161+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "generative-ai", "ai-research"], "entities": ["KRONOS", "QM9", "GEOM-Drugs"], "alternates": {"html": "https://wpnews.pro/news/autoregressive-latent-diffusion-for-3d-molecule-generation", "markdown": "https://wpnews.pro/news/autoregressive-latent-diffusion-for-3d-molecule-generation.md", "text": "https://wpnews.pro/news/autoregressive-latent-diffusion-for-3d-molecule-generation.txt", "jsonld": "https://wpnews.pro/news/autoregressive-latent-diffusion-for-3d-molecule-generation.jsonld"}}