Metraipolis › archive › dc_540f503bedfe

Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints — arXiv:2611.09142

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.09142
License (as archived): CC0-1.0
Archived: 2026-11-09T22:34:52.909Z
SHA-256 of the archived text: c6b6a261228fb0bbd628bf3b009eb3c89cfc8d63ae4c13d9c7d2b098191db370
Stable URL of this page: https://metraipolis.com/documento/dc_540f503bedfe

How to cite

Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints — arXiv:2611.09142 — arXiv (en), https://arxiv.org/abs/2611.09142 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_540f503bedfe (Metraipolis archive dc_540f503bedfe, sha256 c6b6a261228fb0bbd628bf3b009eb3c89cfc8d63ae4c13d9c7d2b098191db370)

BibTeX

@misc{dc540f503bedfe,
  title = {Learning Generative Dynamics for 3D Molecule Generation via Sequential Neuro-Symbolic Constraints — arXiv:2611.09142},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.09142},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_540f503bedfe; sha256 c6b6a261228fb0bbd628bf3b009eb3c89cfc8d63ae4c13d9c7d2b098191db370},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.09142. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have recently emerged as a powerful paradigm for generating 3D molecules. Despite showing remarkable promise, they learn atomic distributions implicitly from data, without explicitly encoding physicochemical rules into their generative dynamics. Consequently, generated samples can be statistically plausible yet chemically invalid. To address this problem, we propose Sequential Neuro-Symbolic Constrained Diffusion (SensDiff), a framework that integrates symbolic rules into generative modeling, enabling the model to internalize scientific priors during training. Central to SensDiff is the observation that the diffusion trajectory of 3D molecule generation exhibits a coarse-to-fine evolution: valid molecules arise by first mitigating macroscopic geometric conflicts and then refining structures toward microscopic chemical consistency through iterative denoising. Accordingly, SensDiff mirrors this dynamic by sequentially enforcing constraints with adaptive weighting during training, progressively steering generation toward valid molecular geometries. Moreover, SensDiff translates domain knowledge into interpretable generative controls, grounding opaque neural denoising in scientific principles. Experiments on molecular benchmarks and real-world constrained generation tasks confirm that SensDiff consistently improves chemical validity while adhering to physicochemical rules and user-specified targets. The code is publicly available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.09142 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-09T22:30:47.321Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).