cd /news/artificial-intelligence/autoregressive-latent-diffusion-for-… · home topics artificial-intelligence article
[ARTICLE · art-56838] src=machinebrief.com ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

Autoregressive latent diffusion for 3D molecule generation

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.

read1 min views1 publishedJul 13, 2026

arXiv:2607.09277v1 Announce Type: new 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.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @kronos 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/autoregressive-laten…] indexed:0 read:1min 2026-07-13 ·