arXiv subjects

Luca Schaufelberger

Publications and source records attributed to Luca Schaufelberger.

4 recordsLinked to original sources

arXiv2026

Manifold Diffusion for Structure Generation of Transition Metal Complexes

Transition metal complexes are central to catalysis, drug design, and materials science, with relevant properties strongly sensitive to their three-dimensional geometry. However, the electronic diversity and unconventional bonding environments of transition metal complexes pose a major challenge for accurate structure generation. In this work, we introduce TMCgen, a manifold diffusion machine learning model that efficiently and accurately generates geometries of transition metal complexes. By formulating the diffusion process over the metal-ligand coordination angles, combined with torsional and rotational diffusion of the ligands, TMCgen focuses on the key geometric degrees of freedom of transition metal complexes. TMCgen shows strong performance in generating accurate coordination environments on a diverse set of experimentally derived bioinorganic and organometallic complexes while requiring only few inference steps, enabling efficient generation. Our results demonstrate the potential of manifold-based generative modeling for data-efficient geometry generation, paving the way for property-conditioned design of transition metal complexes.

cond-mat.mtrl-sci↗

arXiv2026

Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design

Adapting generative foundation models, in particular diffusion and flow models, to optimize given reward functions (e.g., binding affinity) while satisfying constraints (e.g., molecular synthesizability) is fundamental for their adoption in real-world scientific discovery applications such as molecular design or protein engineering. While recent works have introduced scalable methods for reward-guided fine-tuning of such models via reinforcement learning and control schemes, it remains an open problem how to algorithmically trade-off reward maximization and constraint satisfaction in a reliable and predictable manner. Motivated by this challenge, we first present a rigorous framework for Constrained Generative Optimization, which brings an optimization viewpoint to the introduced adaptation problem and retrieves the relevant task of constrained generation as a sub-case. Then, we introduce Constrained Flow Optimization (CFO), an algorithm that automatically and provably balances reward maximization and constraint satisfaction by reducing the original problem to sequential fine-tuning via established, scalable methods. We provide convergence guarantees for constrained generative optimization and constrained generation via CFO. Ultimately, we present an experimental evaluation of CFO on both synthetic, yet illustrative, settings, and a molecular design task. Across these evaluations, CFO achieves consistent increases in reward while ensuring high constraint satisfaction, showcasing its practical utility for constrained generative optimization.

cs.LG↗

arXiv2026

Generating Cyclic Conformers with Flow Matching in Cremer-Pople Coordinates

Cyclic molecules are ubiquitous across applications in chemistry and biology. Their restricted conformational flexibility provides structural pre-organization that is key to their function in drug discovery and catalysis. However, reliably sampling the conformer ensembles of ring systems remains challenging. Here, we introduce PuckerFlow, a generative machine learning model that performs flow matching on the Cremer-Pople space, a low-dimensional internal coordinate system capturing the relevant degrees of freedom of rings. Our approach enables generation of valid closed rings by design and demonstrates strong performance in generating conformers that are both diverse and precise. We show that PuckerFlow outperforms other conformer generation methods on nearly all quantitative metrics and illustrate the potential of PuckerFlow for ring systems relevant to chemical applications, particularly in catalysis and drug discovery. This work enables efficient and reliable conformer generation of cyclic structures, paving the way towards modeling structure-property relationships and the property-guided generation of rings across a wide range of applications in chemistry and biology.

cs.LG↗

arXiv2023

Exploring energy landscapes of charge multipoles using constrained density functional theory

We present a method to constrain local charge multipoles within density-functional theory. Such multipoles quantify the anisotropy of the local charge distribution around atomic sites and can indicate potential hidden orders. Our method allows selective control of specific multipoles, facilitating a quantitative exploration of the energetic landscape outside of local minima. Thus, it enables a clear distinction between electronically and structurally driven instabilities. We demonstrate the effectiveness of this method by applying it to charge quadrupoles in the prototypical orbitally ordered material KCuF$_3$. We quantify intersite multipole-multipole interactions as well as the energy-lowering related to the formation of an isolated local quadrupole. We also map out the energy as a function of the size of the local quadrupole moment around its local minimum, enabling quantification of multipole fluctuations around their equilibrium value. Finally, we study charge quadrupoles in the solid solution KCu$_{1-x}$Zn$_x$F$_3$ to characterize the behavior across the tetragonal-to-cubic transition. Our method provides a powerful tool for studying symmetry breaking in materials with coupled electronic and structural instabilities and potentially hidden orders.

cond-mat.mtrl-sci↗