Zobrazeno 1 - 10
of 89
pro vyhledávání: '"Brehmer Johann"'
Autor:
Brehmer, Johann, Bresó, Víctor, de Haan, Pim, Plehn, Tilman, Qu, Huilin, Spinner, Jonas, Thaler, Jesse
We show that the Lorentz-Equivariant Geometric Algebra Transformer (L-GATr) yields state-of-the-art performance for a wide range of machine learning tasks at the Large Hadron Collider. L-GATr represents data in a geometric algebra over space-time and
Externí odkaz:
http://arxiv.org/abs/2411.00446
Given large data sets and sufficient compute, is it beneficial to design neural architectures for the structure and symmetries of each problem? Or is it more efficient to learn them from data? We study empirically how equivariant and non-equivariant
Externí odkaz:
http://arxiv.org/abs/2410.23179
Modelling the propagation of electromagnetic wireless signals is critical for designing modern communication systems. Wireless ray tracing simulators model signal propagation based on the 3D geometry and other scene parameters, but their accuracy is
Externí odkaz:
http://arxiv.org/abs/2406.14995
Extracting scientific understanding from particle-physics experiments requires solving diverse learning problems with high precision and good data efficiency. We propose the Lorentz Geometric Algebra Transformer (L-GATr), a new multi-purpose architec
Externí odkaz:
http://arxiv.org/abs/2405.14806
We explore the viability of casting foundation models as generic reward functions for reinforcement learning. To this end, we propose a simple pipeline that interfaces an off-the-shelf vision model with a large language model. Specifically, given a t
Externí odkaz:
http://arxiv.org/abs/2312.03881
The Geometric Algebra Transformer (GATr) is a versatile architecture for geometric deep learning based on projective geometric algebra. We generalize this architecture into a blueprint that allows one to construct a scalable transformer architecture
Externí odkaz:
http://arxiv.org/abs/2311.04744
Autor:
Brehmer Johann, Cranmer Kyle, Espejo Irina, Held Alexander, Kling Felix, Louppe Gilles, Pavez Juan
Publikováno v:
EPJ Web of Conferences, Vol 245, p 06026 (2020)
An important part of the Large Hadron Collider (LHC) legacy will be precise limits on indirect effects of new physics, framed for instance in terms of an effective field theory. These measurements often involve many theory parameters and observables,
Externí odkaz:
https://doaj.org/article/0b42c0d742b242e0b131ee959e37f7bd
Problems involving geometric data arise in physics, chemistry, robotics, computer vision, and many other fields. Such data can take numerous forms, for instance points, direction vectors, translations, or rotations, but to date there is no single arc
Externí odkaz:
http://arxiv.org/abs/2305.18415
Embodied agents operate in a structured world, often solving tasks with spatial, temporal, and permutation symmetries. Most algorithms for planning and model-based reinforcement learning (MBRL) do not take this rich geometric structure into account,
Externí odkaz:
http://arxiv.org/abs/2303.12410
Standard imitation learning can fail when the expert demonstrators have different sensory inputs than the imitating agent. This is because partial observability gives rise to hidden confounders in the causal graph. In previous work, to work around th
Externí odkaz:
http://arxiv.org/abs/2211.02667