Metraipolis › archive › dc_236dbadb71f6
ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries — arXiv:2608.20869
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20869
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:31:29.699Z
- SHA-256 of the archived text
4b62c7efc265a7d5a09edd6d56f21b5a9cd3a15c85acac717fed5213e9d88ca7- Stable URL of this page
https://metraipolis.com/documento/dc_236dbadb71f6
How to cite
ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries — arXiv:2608.20869 — arXiv (en), https://arxiv.org/abs/2608.20869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_236dbadb71f6 (Metraipolis archive dc_236dbadb71f6, sha256 4b62c7efc265a7d5a09edd6d56f21b5a9cd3a15c85acac717fed5213e9d88ca7)
BibTeX
@misc{dc236dbadb71f6,
title = {ReCurveflow: A Flow Matching Framework that Learns Curved Reaction Trajectories to Predict Transition State Geometries — arXiv:2608.20869},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20869},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_236dbadb71f6; sha256 4b62c7efc265a7d5a09edd6d56f21b5a9cd3a15c85acac717fed5213e9d88ca7},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Predicting transition states (TS) in chemical reactions is crucial, as they provide insights into reaction mechanisms. Recent work on TS prediction have focused on flow matching supervised on straight linear paths that do not align with actual reaction trajectories. We propose a novel flow matching-based framework ReCurveflow that learns to predict TS geometries supervised on continuously curved reference paths interpolated from a full NEB-derived band of molecular geometries. We also introduce off-path correction, which grants ReCurveflow with the ability to produce corrective velocity fields when engaged off-path geometry states during inference rollout, leading to better resistance against exposure bias and accuracy in TS prediction. Across three data splits and six evaluation metrics, ReCurveflow achieves the best result on the majority of split-metric combinations against seven baselines. Qualitative analyses further show that ReCurveflow generates reaction trajectories with energy profiles that closely track the reference NEB path, provides initializations that ease the NEB optimization bottleneck, and exhibits the intended corrective behavior in its learned velocity fields. The ReCurveflow codebase is publicly available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-24 in cs.LG). Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2608.20869 — 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 2026-10-18T10:27:55.996Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).