English
Related papers

Related papers: Lorentz-Equivariant Geometric Algebra Transformers…

200 papers

Owing to their ability to both effectively integrate information over long time horizons and scale to massive amounts of data, self-attention architectures have recently shown breakthrough success in natural language processing (NLP),…

Local Lorentz transformations play an important role in teleparallel gravity theories, in which a tetrad is conventionally employed as a fundamental field variable describing the gravitational field. It is commonly understood that…

General Relativity and Quantum Cosmology · Physics 2022-11-09 Manuel Hohmann

Large language models have seen widespread adoption in math problem-solving. However, in geometry problems that usually require visual aids for better understanding, even the most advanced multi-modal models currently still face challenges…

Computer Vision and Pattern Recognition · Computer Science 2024-06-18 Shihao Cai , Keqin Bao , Hangyu Guo , Jizhi Zhang , Jun Song , Bo Zheng

We use Lie-algebraic arguments to classify Lorentz-invariant theories of massless interacting scalars that feature coordinate-dependent redundant symmetries of the Galileon type. We show that such theories are determined, up to a set of…

High Energy Physics - Theory · Physics 2018-10-31 Mark P. Bogers , Tomas Brauner

Fefferman and Graham showed some time ago that four dimensional conformal geometries could be analyzed in terms of six dimensional, ambient, Riemannian geometries admitting a closed homothety. Recently it was shown how conformal geometry…

High Energy Physics - Theory · Physics 2014-11-21 Roberto Bonezzi , Emanuele Latini , Andrew Waldron

Geometric Graph Neural Networks (GNNs) and Transformers have become state-of-the-art for learning from 3D protein structures. However, their reliance on message passing prevents them from capturing the hierarchical interactions that govern…

Machine Learning · Computer Science 2025-12-09 Chang Liu , Vivian Li , Linus Leong , Vladimir Radenkovic , Pietro Liò , Chaitanya K. Joshi

Formulae relating one and the same force in two inertial frames of reference are derived directly from the Lorentz transformation of space and time coordinates and relativistic equation for the dynamic law of motion in three dimensions. We…

Physics Education · Physics 2007-05-23 Valery P. Dmitriyev

On the base of the distinction between covariant and contravariant metric tensor components, a new (multivariable) cubic algebraic equation for reparametrization invariance of the gravitational Lagrangian has been derived and parametrized…

High Energy Physics - Theory · Physics 2014-11-20 Bogdan G. Dimitrov

On the base of the distinction between covariant and contravariant metric tensor components, an approach from algebraic geometry will be proposed, aimed at finding new solutions of the Einstein's equations both in GTCCCM and in standard…

High Energy Physics - Theory · Physics 2009-10-22 Bogdan G. Dimitrov

We present the first formulation of linearised gravity in four dimensions which is manifestly Lorentz covariant and democratic, i.e. treats the two frames related by electric-magnetic duality on equal footing. It is well-known that…

High Energy Physics - Theory · Physics 2026-04-16 Calvin Y. -R. Chen , Euihun Joung , Karapet Mkrtchyan

Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and…

Machine Learning · Computer Science 2022-03-15 Wenbing Huang , Jiaqi Han , Yu Rong , Tingyang Xu , Fuchun Sun , Junzhou Huang

Although recent deep learning methods, especially generative models, have shown good performance in fast magnetic resonance imaging, there is still much room for improvement in high-dimensional generation. Considering that internal…

Computer Vision and Pattern Recognition · Computer Science 2022-12-13 Wei Zhang , Zengwei Xiao , Hui Tao , Minghui Zhang , Xiaoling Xu , Qiegen Liu

Geometry-aware optimizers such as Newton and natural gradient can improve conditioning in deep learning, but scalable variants such as K-FAC, Shampoo, and related preconditioners usually impose structural approximations early, often…

Machine Learning · Computer Science 2026-05-07 Simon Dufort-Labbé , Pierre-Luc Bacon , Razvan Pascanu , Simon Lacoste-Julien , Aristide Baratin

Determining atomistic structures from characterization data is one of the most common yet intricate problems in materials science. Particularly in amorphous materials, proposing structures that balance realism and agreement with experiments…

Disordered Systems and Neural Networks · Physics 2026-03-25 Jiawei Guo , Daniel Schwalbe-Koda

The Large Hadron Collider at CERN produces immense volumes of complex data from high-energy particle collisions, demanding sophisticated analytical techniques for effective interpretation. Neural Networks, including Graph Neural Networks,…

While large language models (LLMs) show great potential in temporal reasoning, most existing work focuses heavily on enhancing performance, often neglecting the explainable reasoning processes underlying the results. To address this gap, we…

Computation and Language · Computer Science 2025-05-22 Zihao Jiang , Ben Liu , Miao Peng , Wenjie Xu , Yao Xiao , Zhenyan Shan , Min Peng

Lattice metamaterials enable lightweight, multifunctional structures, yet homogenization-based evaluation of their effective properties remains computationally expensive. Neural surrogates offer speed but often lack the accuracy and…

Graphics · Computer Science 2026-04-30 Yu Xing , Yang Liu , Tianyang Xue , Lin Lu

Knowledge Graph Completion (KGC), which aims to infer missing or incomplete facts, is a crucial task for KGs. However, integrating the vital structural information of KGs into Large Language Models (LLMs) and outputting predictions…

Computation and Language · Computer Science 2025-06-02 Kangyang Luo , Yuzhuo Bai , Cheng Gao , Shuzheng Si , Yingli Shen , Zhu Liu , Zhitong Wang , Cunliang Kong , Wenhao Li , Yufei Huang , Ye Tian , Xuantang Xiong , Lei Han , Maosong Sun

Contrary to the conventional view point of quantization that breaks the gauge symmetry, a gauge invariant formulation of quantum electrodynamics is proposed. Instead of fixing the gauge, some frame is chosen to yield the locally invariant…

High Energy Physics - Theory · Physics 2007-05-23 Taro Kashiwa , Yasushi Takahashi

Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise. Motivated by recent advances in geometric representation learning, we…

Machine Learning · Computer Science 2019-10-30 Qi Liu , Maximilian Nickel , Douwe Kiela