AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation
Abstract
Predicting metal-organic framework (MOF) structures from given building blocks requires recovering their positions and orientations in a periodic crystal. The spatial effects of rotation errors are geometry-dependent and anisotropic. The same angular error can produce different atomic displacements depending on block size, shape, and rotation axis. Angular error alone, without reference to the specific block geometry, therefore cannot fully describe the spatial consequences of a pose error. We introduce AnchorPose, a meso-grained pose generation framework that incorporates this geometric dependence into its generative representation. It represents each block through a small set of representative atoms, combines their local geometry with the current spatial state, and generates their coordinates with Bayesian Flow Networks. Known atom correspondences enable rigid alignment to recover complete building-block poses and return geometrically consistent points to the generation process. This design connects point-level spatial prediction with block-level structural constraints. Geometry participates in the pose state and its prediction, while rigid reconstruction preserves intra-block structure without treating all atomic coordinates as assembly variables. On the MOF benchmark, AnchorPose improves single-candidate match rates over the compared block-level and all-atom baselines.
Related
- An assembly of two slender anisotropic beams through a very thin adhesive layer
- Cross-geometry transfer and model collapse in point cloud calorimeter shower generation
- Transferable Fast Calorimeter Shower Generation via Multi-Geometry Pre-training
- Probing Scalar Polarization with Next-Generation Gravitational-Wave Detectors: The Roles of Detector Geometry and Source Inclination
- Algebraic solutions for propagation of elastic SH-waves through an isotropic inhomogeneous geometry
BibTeX
@misc{peng2026anchorpose,
title = {{AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation}},
author = {Zhonglong Peng and Rui Jiao and Chang Chen and Geng Zhong and Qiuliang Liu and Shifeng Jin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.05843},
eprint = {2610.05843},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.05843},
}
RIS
TY - UNPB
TI - AnchorPose for Geometry-Aware MOF Assembly through Meso-Grained Pose Generation
AU - Zhonglong Peng
AU - Rui Jiao
AU - Chang Chen
AU - Geng Zhong
AU - Qiuliang Liu
AU - Shifeng Jin
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2610.05843
UR - https://arxiv.org/abs/2610.05843
AB - Predicting metal-organic framework (MOF) structures from given building blocks requires recovering their positions and orientations in a periodic crystal. The spatial effects of rotation errors are geometry-dependent and anisotropic. The same angular error can produce different atomic displacements depending on block size, shape, and rotation axis. Angular error alone, without reference to the specific block geometry, therefore cannot fully describe the spatial consequences of a pose error. We introduce AnchorPose, a meso-grained pose generation framework that incorporates this geometric dependence into its generative representation. It represents each block through a small set of representative atoms, combines their local geometry with the current spatial state, and generates their coordinates with Bayesian Flow Networks. Known atom correspondences enable rigid alignment to recover complete building-block poses and return geometrically consistent points to the generation process. This design connects point-level spatial prediction with block-level structural constraints. Geometry participates in the pose state and its prediction, while rigid reconstruction preserves intra-block structure without treating all atomic coordinates as assembly variables. On the MOF benchmark, AnchorPose improves single-candidate match rates over the compared block-level and all-atom baselines.
ER -