arXiv Machine Learning July 30, 2026 By Michelangelo Domina, Michele Ceriotti

Using large language models to probe the limits of atom-centered structural descriptors

Read the original on arXiv Machine Learning →

arXiv:2607. 26984v1 Announce Type: cross Abstract: Mapping an atomic structure to a compact set of geometric descriptors is an essential step in any machine-learning application to atomic-scale modeling.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

llms

arXiv Machine Learning

4d ago

Invariant Atoms: Sparse Coordinates of Local Semantic Geometry in Language Model Representations

arXiv:2609.36451v1 Announce Type: new Abstract: Large language models often preserve meaning despite substantial changes in wording, style, and syntax, while small semantic edits can systematically a...

By Muhammad Ahtesham, Xin Zhong

llms

arXiv AI

Jul 7

NextCrystal: a Symmetry-Driven Generative Framework for Crystal Structure Prediction

arXiv:2602. 17176v4 Announce Type: replace-cross Abstract: Crystal structure prediction (CSP), which aims to predict the 3D atomic arrangement of a crystal from its composition, is central to materials discovery and mechanistic understanding.

By Jinming Mu, Lixin He, Xudong Zhu, Shi Yin

llms diffusion benchmarks

arXiv AI

Jul 1

CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM

arXiv:2606. 31332v1 Announce Type: new Abstract: Protein automodeling from cryo-EM density maps faces unique challenges in enforcing physicochemical validity and managing conformational heterogeneity.

By Minzhang Li, Mingrui Li, Weichen Qin, Qihe Chen, Sixian Shen, Yuan Pei, Jiakai Zhang, Jingyi Yu

multimodal benchmarks

arXiv Machine Learning

Sep 24

What Converges in the Platonic Representation Hypothesis? Structure over Geometry

The paper investigates the Platonic Representation Hypothesis, which posits that more capable models converge toward shared representations. By distinguishing relational structure (which samples are related) from metric geometry (quantitative relations like distances), the authors develop a controlled $2 imes2$ framework to evaluate both aspects at local and global scales. Their findings show that relational structure consistently converges across vision‑language and video‑text models, while metric geometry converges much more weakly, a pattern that persists even when using a Riemannian metric approximation.

By Junwon You, Mihyun Jang, Sangwoo Mo, Jae-Hun Jung

llms multimodal safety

arXiv AI

Aug 5

Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning

arXiv:2608. 02930v1 Announce Type: new Abstract: We revisit higher-arity atomic concept learning through the geometry of hypercubes and hyperplanes of ground instances.

By Irene Tsapara

arXiv Machine Learning

Aug 7

Physics-Based Molecular Fingerprints from Spectral Graph Theory Provide Efficient Geometry-Aware Measures of Chemical Similarity

arXiv:2608. 05336v1 Announce Type: cross Abstract: Molecular representations are essential for the evaluation of molecular similarity and the development of structure-property relationships.

By Jacob W. Toney, Ayleen Y. Farnood, Samir Darouich, Heather J. Kulik

rag

One email a morning, machine-written

Related stories

Invariant Atoms: Sparse Coordinates of Local Semantic Geometry in Language Model Representations

NextCrystal: a Symmetry-Driven Generative Framework for Crystal Structure Prediction

CryoACE: An Atom-centric Framework for Accurate and Automated Model Building in Cryo-EM

What Converges in the Platonic Representation Hypothesis? Structure over Geometry

Hypercubes, Hyperplanes, and Constraint-Induced Complexity Collapse in Atomic Concept Learning

Physics-Based Molecular Fingerprints from Spectral Graph Theory Provide Efficient Geometry-Aware Measures of Chemical Similarity